PRICE BEHAVIOUR OF MULBERRY SILK COCOON IN RAMNAGAR AND SIDDLAGHATTA MARKET – A

STATISTICAL ANALYSIS

Thesis submitted to the University of Agricultural Sciences, Dharwad in partial fulfilment of the requirements for the

Degree of Master of Science (Agriculture)

in

AGRICULTURAL STATISTICS

By R. BHARATHI

DEPARTMENT OF AGRICULTURAL STATISTICS COLLEGE OF AGRICULTURE, DHARWAD

UNIVERSITY OF AGRICULTURAL SCIENCES, DHARWAD - 580 005

JUNE, 2009

ADVISORY COMMITTEE

DHARWAD (Y. N. HAVALDAR) JUNE, 2009 MAJOR ADVISOR

Approved by :

Chairman : ____________________________ (Y. N. HAVALDAR)

Members : 1. __________________________ (S. N. MEGERI)

2. __________________________ (BASAVARAJ N. BANAKAR)

3. __________________________ (B. L. PATIL)

4. __________________________ (G. M. PATIL)

C O N T E N T S

Sl. No. Chapter Particulars Page No.

CERTIFICATE

ACKNOWLEDGEMENT

LIST OF TABLES

LIST OF FIGURES

LIST OF PLATES

LIST OF APPENDICES

1 INTRODUCTION

2 REVIEW OF LITERATURE

2.1. Compound growth rates

2.2 Behaviour of price and arrivals

2.3. Market integration

2.4. Box-Jenkins model and its application

3 METHODLOGY

3.1 Description of the selected markets

3.2 Nature and sources of data

3.3 Analytical tools and techniques

4 RESULTS

4.1 Growth pattern in arrivals and prices of cocoon

4.2 Behaviour of arrivals and prices of cocoon

4.3 Market integration

4.4 Forecasting of arrivals and prices

5 DISCUSSION

5.1 Growth rates in arrivals and prices of cocoon

5.2 Behaviour of arrivals and prices of cocoon

5.3 Market integration

5.4 Forecasting of arrivals and prices

6 SUMMARY AND POLICY IMPLICATIONS

REFERENCES

APPENDICES

LIST OF TABLES

Table No.

Title Page No.

3.1 Computation of centered 12 month moving average

3.2 Average of percentage centered 12 month moving average and computation of seasonal index for observation

3.3 Tabular format of obtaining cyclical component

4.1 Growth rates in arrivals and prices of cocoon from Ramnagar and Siddlaghatta market

4.2 Seasonal indices of monthly arrivals and prices of cocoon in Ramnagar and Siddlaghatta market

4.3 Correlation coefficient between quantity and price in Ramnagar and Siddlaghatta market (year wise)

4.4 Correlation between arrivals and prices of cocoon in Ramnagar and Siddlaghatta market (120 months )

4.5 Concurrent deviation between Ramnagar and Siddlaghatta market

4.6 ACF and PACF of monthly arrivals and prices of cocoon in Ramnagar market.

4.7 Residual analysis of Ramnagar and Siddlaghatta market

4.8 Actual and Forecasted values for arrivals of cocoon in Ramnagar market

4.9 Actual and Forecasted values for prices of cocoon in Ramnagar market

4.10 Selected measures of predictive performance of the Box Jenkins model

4.11 ACF and PACF of monthly arrivals and prices of cocoon in Siddlaghatta market

4.12 Actual and Forecasted values for arrivals of cocoon in Siddlaghatta market

4.13 Actual and Forecasted values for prices of cocoon in Siddlaghatta market

LIST OF FIGURES

Figure No Title Page No.

4.1 Seasonal indices of arrivals in Ramnagar and Siddlaghatta market

4.2 Seasonal indices of prices in Ramnagar and Siddlaghatta market

4.3 Trend component of arrivals of cocoon in Ramnagar market

4.4 Trend component of prices of cocoon in Ramnagar market

4.5 Trend component of arrivals of cocoon in Siddlaghatta market

4.6 Trend component of prices of cocoon in Siddlaghatta market

4.7 Cyclical trend of arrivals in Ramnagar and Siddlaghatta markets

4.8 Cyclical trend of prices in Ramnagar and Siddlaghatta markets

4.9 Ex-ante and ex-post forecast of cocoon arrivals in Ramnagar market

4.10 Ex-ante and ex-post forecast of cocoon prices in Ramnagar market

4.11 Ex-ante and ex-post forecast of cocoon arrivals in Siddlaghatta market

4.12 Ex-ante and ex-post forecast of cocoon prices in Siddlaghatta market

LIST OF PLATES

Plate No

Title Page No.

1 Ramnagar cocoon market

2 Siddlaghatta cocoon market

3 Display of cocoons in market yard on metal platform

4 Market officer in final price bidding

LIST OF APPENDICES

Appendix No

Title Page No.

I State wise Area and Raw Production of Mulberry Silk

II Export earnings from silk items

III Country wise silk export earnings

1. INTRODUCTION

Silk is the most elegant among textiles in the world, as it remains most loved fibre throughout the world. It is literally just a continuous protein filament secreted by specific types of caterpillars commonly known as silk worms. The endearing qualities of silk are natural sheen, inherent affinity for rich colours, high absorbance and light weight with high durability. Hence it is acclaimed as the queen of textiles and also Aristocrat good. Silk is associated with human happiness (i.e) on festivals, marriages, functions, etc., all people from children to adults would like silk clothes.

Mulberry silk is produced from silk worm (Bombyx mori.L) which feeds on mulberry leaves. Silk worm rearing is location specific, a temperature ranging from 70 F to 85 F, humidity in the range of 60 to 80 % and the rainfall of about 600 mm found suitable. Silkworms produce the cocoon in about 25-30 days, after which worms spin cocoons. These cocoons are sold to the reelers at the regulated cocoon markets. The reelers convert them into silk yarn. In the major silk producing states, there are well established cocoon markets for the sale of cocoons. The revealed silk is bought by weavers and this transaction takes place through the silk exchanges.

Silk scenario in India

In global market, silk accounts for only 0.2 % of the total world production of all textile fibres. India is the second largest producer of silk in the world, next to China and has a 12% share in the global raw silk production. The annual silk production in the country is about 16,000 million tonnes with annual consumption of silk is around 26,000 million tonnes and foreign exchange earning from silk goods export is over Rs 300 crores. Silk production has increased from about 4,000 tonnes in 1980 to about 16,245 million tonnes in 2008, (Kshama et al, 2008). Silk production in small quantities has been widespread but it flourished only in China, Japan, Korea, India and more recently in Brazil and USSR.

Karnataka ranks first in production followed by Andhra Pradesh and West Bengal with 8,240.00, 4,485.32 and 1,660.36 million tonnes respectively (Appendix I).

Out of the total production, about 55 % is accounted by Karnataka, it was followed by Andhra pradesh, West Bengal and Tamilnadu. The five traditional states where sericulture is practiced are Karnataka, Andhra pradesh, Tamil nadu, West Bengal, Jammu and Kashmir. These states accounts for most of the mulberry silk production in the country.

India has the unique distinction of producing all the four types of silk viz., mulberry, tasar, muga and eri. Among them, mulberry silk is predominant and accounts for 88 % of the total natural silk produced in India. Around 53,000 villages of India are involved in growing silk cocoons. The area under mulberry cultivation in India is 1,91,893 hectares with raw silk production of 16,245 million tonnes.

Karnataka accounts for 25% of the country’s silk export. Silk knit fabrics could contribute 5-10% to the total export of silk materials, currently worth Rs 1,500 crores from the country. Japan, China and India are the leading countries in the production of silk and other materials. There is demand for the Indian silk items from America, Spain, Germany, Italy and East Europe. 75 % of the Indian production was used domestically and only 25% is exported (Appendix II).

Export scenario

USA, UK, UAE, Italy and German were the top five countries imported Indian silk goods in value terms during the year 2007-08 and accounted for the 23.2%, 14.2%, 7.9%, 6.4% and 5% respectively of the total export earnings (Appendix III).

Scope for sericulture

Sericulture being a small enterprise provides ample opportunity to reach target groups especially small and marginal farmers. It has the advantage of addressing simultaneously and rapidly towards several development priorities. Sericulture provides 1) employment and income generation in rural areas 2) high participation of low income and target social groups 3) good comparative advantage and growth prospects 4) potential for export earnings 5) providing a greater role for development 6) good downstream employment

impact of raw silk production on the industrial sector. All these combined features make sericulture an attractive sector for further development.

The biggest problem in world silk economy is the prevailing price instability in cocoon and raw silk markets. The 21

st congress of the International Sericultural Commission (ISC),

devised a policy to safeguard the interests of developing countries against the influx of low priced silk and silk commodities.

Our problem in the world silk economy is the prevailing price instability in the cocoon and raw silk markets. This is accentuated by the seasonal production of cocoons, which means that there are periods when farmers and reelers have no work at all in some areas of countries. If price instability is reduced, the gains could be increased to considerable extent and it has a very high degree of backward and forward linkages as it encompass both agriculture and industry. Though sericulture plays an important role in Indian economy, there exists a serious problem of fluctuation in silk cocoon prices in markets.

Hence, the present study is conducted with the following specific objectives.

1) To study the growth in arrivals and prices of cocoon in the selected markets

2) To study the behaviour of price of cocoon in the selected markets

3) To analyze the market integration of selected markets

4) To forecast the price of cocoon in the selected markets

2. REVIEW OF LITERATURE

In this chapter an attempt has been made to critically review the literature of the past research work relevant to the present study. The available literature on the subject has been reviewed and presented under the following headings

2.1. Compound growth rates

2.2 Behaviour of price and arrivals

2.3. Market integration

2.4. Box-Jenkins model and its application

2.1 Compound growth rates

Rath (1980) examined the growth rates of agricultural production in India during 1955 to 1978. The total agricultural production was found to grow at an average rate of 2.48% per year during this period. Growth rate for cereal production was 3.22% and that for non-food grains was 2.70% annum.

Chengappa (1981) made a study on growth rates of area, production and productivity of coffee in India. A linear model of the type Y = a + b

t an exponential model of the type Y =

abt were used and the corresponding growth rates were worked out. The exponential function

yielded a good fit of the compound growth for coffee.

Mruthyujaya et al. (1982) compared the pace and pattern of agriculture output growth in Karnataka with that of all India. The study used different trend functions to estimate the growth rates. One of the major findings that emerged out of the study was that performance of agriculture in Karnataka was comparatively better than that of all India except in the case of sugarcane and oilseeds.

Bisalaiah and Patil (1987) studied the trends of major crops in Karnataka. They found that ragi, bajra and pulses have expressed higher output growth rate, whereas rice and sorghum had recorded lower growth rates during the period 1966-67 to 1977-78. The output growth in case of sorghum, ragi, rice and bajra had shifted from area-cum-productivity led growth during pre-green revolution period to productivity led during the green revolution period. They concluded that productivity increase had contributed substantially to the growth in output of most of the food grains and that of agricultural output performance of Karnataka, which was higher than the all India performance.

Tripathy and Srinivas Gowda (1993) used the exponential function to estimate and compare the district wise compound growth rates of area, yield and production of groundnut in Orissa during the seventies (1970-71 to 1979-80) and eighties (1980-81 to 1989-90). The structural change in the growth pattern between the decades was examined employing a chow’s test. Despite negative growth rates of yield in both decades growth rate of production had been impressive, which increased from 4.56 percent per annum in seventies to 7.8 percent in the eighties mainly because of high rate in area increase. The structural change in the growth function especially that of yield and production in almost all the district covered was apparent from the significant ‘F’ values obtained in the chow’s test.

Thampan (1994) observed the evidence for declarations in Indian food grains production in the 1980’s. The trend analysis of different crops over sixth and seventh five years plan periods covering the eighties revealed that growth in production during VII plan period was much less for all the cereals and pulses compared to that during VI plan period. In the case of rice, the annual growth rate of production declined from 7.8 to 5.4 % between the plan periods and for wheat the decline was more from 6.9% to 2.8%. The reasons attributed for the declaration of output growth were indiscriminate use of chemical inputs and neglect of soil health.

Patel et al. (1996) studied the compound growth rate of pulses in selected districts of Gujarat for the period 1949-91. For Gujarat state as a whole, the production growth rate for the study period worked out to 3.05 %. The growth rate in area and yield was 0.7% and 2.19% respectively. Surendranagar district registered the highest growth rate in area (4.78%)

and production (6.82%). The figure of coefficient of variation was found to be 43.63 % for production, 22.65% for area and 29.22% for yield.

Singh et al. (1997) while assessing the regional variations in agricultural performance in India, estimated the compound growth rates of area, production and yield of pulses by fitting log linear function of the form, log Y = a + b

t. The data were analyzed for three time

period viz.,

Period I (1960-61 to 1967-68)

Period II (1968-69 to 1980-81)

Period III (1981-82 to 1992-93)

In almost all the states selected for analysis, the growth rate of pulses, significant growth rates were observed with respect to area.

Ashalatha (2000) studied the growth in cashew exports from India over the period 1956-57 to 1998-99, using an exponential growth function of the form Yt = ab

te

u. The results

of the study revealed that there was a significant growth in case of export quantity, total value and unit value of exports.

Legesse (2000) found that during eighties wheat area showed a declining growth rate (i.e.) 3.94 per cent per annum but production and productivity showed a negative growth rate. During nineties the Karnataka state recorded a significant positive growth rate of 3.47 per cent in area while in production the state recorded a mild growth, productivity showed a negative growth rate.

Kaur et al. (2002) computed compound growth rate to examine the trends in area, production and productivity of pulses. The study revealed that growth rates in production and productivity of total pulses in India were found to be significant and positive.

Desai (2001) analyzed the growth rates of mango exports to five major importing countries viz., UAE, UK, Netherland, Hong Kong and Japan for the period 1990 to 1998. Remaining countries importing mango from India were grouped together as others. Fresh mango exports to Japan registered a growth rate of 33.87 per cent followed by others (12.97%), Nether lands (7.50%) and UK (5.76%). The total growth in export of fresh mango was 9.01 per annum.

Shwetha (2003) computed compound growth rate for production and export of shrimp, squid and ribbon fish for the period from 1990 to 2000. The result of the study revealed that there was a significant positive growth in case of total production and exports of shrimp, squid and ribbon fish.

Nisha (2004) studied the growth rate of groundnut in India from 1980-1988 and 1991-1994. The results revealed that, in the pre-liberalization period, there is a negative growth rate both in quantity and value. But in the post liberalization period (after 1991), the quantity of exports showed an increasing trend whereas the value of exports showed a declining trend.

Varuna (2005) studied the compound growth rate in black pepper in India during 1980-81 to 2002-03. The results showed that the area under black pepper increased at the rate of 3.63 per cent per annum. The production and productivity increased at 5.20 % and 1.52 % per annum respectively, which showed positive and significant growth.

Dudhat (2006) computed the compound growth rates for quality seeds for the study of 1980-81 to 2000-01 in Gujarat. The growth rates under quality seeds found positive in both 1981-91 (2.81%) and 1992-01 (2.26%) period but it was statistically non- significant, whereas in overall period (1981-01), the growth rate was positive and statistically significant. Almost the same pattern of growth rates was observed in production but in case of yield, the negative growth rates was observed in all the periods under study and it was found statistically significant in 1981-91 (-3.83%).

Vinaya (2007) used compound growth rates to find the growth in area, yield and production of rice. The results revealed that in Karnataka, area under rice increased from 1.12 million hectares during 1985-86 to 1.14 million hectares in 2004-05. The area increased at a compound growth rate of 1.01 percent per annum. For the same period, production increased

from 2.38 million tonnes to 2.51 million tonnes at an annual compound growth rate of 2.21 percent, where as yield increased at the rate of 1.27 percent.

2.2 Behaviour of price and arrivals

Kahlon and Singh (1968) studied price fluctuation in groundnut, employing the seasonal indices method on the data from important groundnut markets of Punjab. They showed that the highest percentage of produce was sold in the peak production period- October to January. The index of seasonal price variation was at the lowest in October followed by November and reached the peak in August.

Gill and Johl (1970) analyzed the seasonal patterns in the gram prices at Sirsa market for fifteen years between 1952 and 1966. The index for the arrivals was the highest in the month of May at 270.05 and price index was at its lowest in May at 92.59. Violent seasonal fluctuations led them to conclude that production was over dependent on nature, storage facilities were lacking and the zonal movement policies were poorly conceived.

Gurumallappa (1972) studied the relationship between the arrivals and prices of groundnut in Raichur and found that prices were high when the arrivals were also high.

The annual and seasonal movement of arecanut prices was analysed by Shenoy and Ravindran (1972). The study showed that the average monthly whole sale prices (of all varieties viewed) generally ruled low in the harvest season

George and Govindan (1975) opined that the supply and price of many agricultural commodities follow some what regular cycles. The monthly wholesale price data of potatoes in Ahmedabad market for nine years 1996 to 1974 were subjected to Harmonic analysis. It revealed the presence of a time trend, a 12 month cycle and a three year cycle. Estimators were obtained by the method of least squares. The elasticities for short run, seasonal and long run were worked out. A method was suggested by them to compute the adjustment lags (i.e.) the time and its impacts on arrivals corresponding to seasonal cycles were also studied.

Govardhan (1978) analysed the marketing of dry chillies in Karnataka. His study showed on inverse relationship between the price and arrivals series. Seventy two to eighty percent of the total produce arrived at the markets between November and April. In this period, prices were at relatively low levels.

Mundinamani et al. (1991) used the monthly time series data on market arrivals and prices of groundnuts for the period 1960/61 -1983/84 collected from the regulated markets of Gadag and Hubli to estimate indices, trend equations and coefficients of variation. The pattern of market arrivals of groundnut indicates a seasonal character. The prices of groundnuts were found to be a function of market arrivals only in the short- run. The seasonal pattern of market arrivals and the resulting short-run instability in groundnut prices could be eliminated by using a package of measures. In the long-run, prices are influenced not only by market arrivals but also by other factors such as the general rise in prices and the steady rise in demand for groundnut products.

Kasar et al. (1996) studied behaviour of price and arrivals of red chillies in Maharashtra seasonal indices of arrivals of red wet chillies begin in October and end in April. While that of red dry chillies start in May and end in September. The arrivals of red wet chillies were maximum during December to march when the corresponding prices were relatively low. The arrivals of red wet chillies were low during October, November and April. During these months prices were relatively at higher level. By and large, it appears that when the seasonal index of arrivals of red wet chillies was more during December to March, the seasonal index of prices was at a low level. On the other hand, when the seasonal index of arrivals of red dry chillies was low (May to September) the price index of chillies was at a very high level.

Keith et al. (1997) examined seasonal potato price indices for two major wholesale potato markets of Delhi and Kolkata. It was cleared that potato prices typically double between the end of harvest in March and the onset of summer in July and August. The most rapid increase in potato prices occurs in April and May. There was a slight dip in price in the Delhi market in mid summer which may reflect the arrival of a summer crop. Prices then continue to rise until peaking in September or October when existing stocks are lowest and just prior to the arrivals on the market of early potatoes in months of November and December.

Ravikumar et al. (2001) concluded that in general, arrivals showed mixed trend, whereas, prices showed an increasing trend for the selected commodities in Anakapalle regulated market of Andhra Pradesh. There exists an inverse relationship between seasonal indices of arrivals and prices of selected commodities. Therefore, the policy implication lies in encouraging the farmers to dispose their produce at the opportune time to get good remunerative prices. It requires providing finance to farmers and better storage facilities either at village level or at market level so as to spread the arrivals reasonably in the lean months of the year.

Rajashekar (2005) studied the cyclic trend in arrivals and prices of vegetables for Mysore and K.R.Market. K.R.Market cycle was smoothening with maximum cycle effects in case of 156 months. The slump was observed with 35 months indicating that the high arrivals observed in every 30 months. The cyclical components were observed only in weekly prices for K.R.Market.

Mithlesh (2006) studied the trend in dairy industry in India during pre WTO and post WTO period. In the pre WTO period (1985-86 to 1994-95), the import value of whole milk powder recorded increasing trend which was non significant but in post WTO period trend was decreasing non-significantly except in 1999 to 2001.

Punitha (2007) studied the seasonal indices and trend in arrivals and prices of maize and ground nut in Davengere market and Hubli market. In case of maize, Davangere market showed increasing trend in arrivals but Hubli market showed stagnant trend and both the markets showed an increasing trend in prices. In Davangere market significant and positive relationship between arrivals and prices was observed for maize. Whereas, in Hubli market non-significant and negative relationship was observed.

Yogisha (2007) computed trend in arrivals and prices of potato in Chikkaballapur, Chintamani, kolar and Srinivaspur during 1994-95 to 2004-05. The results shows that in the initial years potato arrivals was increasing and in the mid period it started decreasing while in the later period the arrivals again increased in all markets except Srinivaspur. In case of price trend pattern, decreasing trend in prices of potato in later period except Bangalore and Chintamani may be because of increased arrivals of potato to these markets.

2.3 Market Integration

Krishnaswamy (1975) studied the behaviour of market arrivals of groundnut prices of Rajasthan. He observed that the six out of eight cases studied the market arrivals were positively related to prices.

Bhat (1980) studied the movement of paddy and groundnut prices in the selected market of Karnataka. He employed zero order correlation coefficient analysis for analysing market integration. Further, he suggested a strong integration of markets in price formation indicating the influence of price in one market over the prices in other markets. The “r” values were higher in the cases of bigger markets compared to smaller markets indicating the influence of traders participation in determining the degree of market integration.

Ejiga and Robinson (1981) analysed the market integration in terms of storage cost of cowpea in Nigeria and showed that on an average, the stock had to be held for about eight months to secure maximum gains. Significantly, there was high degree of variability from year to year in both price and arrivals. Suggesting that a farmer or a trader could not be assured of profit from storage every year.

Mundinamani (1985) analysed the market concentrations by commission agents in the selected market of groundnut in Dharwad district. The author found that the top commission agents controlled about two thirds of the total quantity of groundnut handled in Hubli market and one third in Gadag market, indicated a high degree of concentration in purchase in Hubli market compared to Gadag market.

Singhal (1986) studied five primary and one terminal markets in Uttar Pradesh to analyse spatially and temporally, the rape-seed mustard price structure using correlation coefficients technique for spatial analysis. He found that almost every year there were periods of attack 6 to 8 weeks at strength when the terminal market (Kanpur) price was considerably in excel of the primary market price (after taking transport costs etc. into account). It was concluded that while the primary and terminal markets were spatially disintegrated.

Nagaraj et al. (1987) studied spatial integration of silk cocoon markets in Karnataka. The Haugh‘s test based on cross correlation coefficient was employed to examine the dependence of prices in various silk cocoon markets with that of Ramnagaram prices. Results revealed that the silk cocoon markets in Karnataka were spatially integrated and there by price efficient.

Devaiah et al. (1988) studied spatial integration and price leadership of Ramnagaram cocoon market over other markets through Granger’s causality test. This test was performed on the price series of fourteen markets, which were filtered using an ARIMA model. The cross correlation coefficient of the residuals of the Ramnagaram silk cocoon prices with other markets was relatively high at lag 0. Hence it was concluded that prices were determined spontaneously in all the markets and no specific lead- lag relations existed between them. The markets were observed to be spatially integrated and price efficient.

Prabhakara (1988) studied the market integration of two major cocoon markets in Karnataka viz. Ramnagaram and Vijayapura. It was found that both the markets were highly integrated as indicated by a very high correlation coefficient of 0.947 between the seasonal indices of prices (0.601) in different markets was also significant at one per cent level. This confirmed the observations made earlier that the two markets being closely integrated and spatially efficient.

Prabhakara (1988) analyzed price transmission between silk prices at Bangalore silk exchange and cocoon markets. The estimated price transmission elasticities for Vijayapura and Ramnagaram markets were observed to be close to unity. This kind of elasticity of price transmission between two stages of marketing is ideal, provided the price spread is realistic and markets being price efficient.

Naik and Babu (1993) analyzed the prices of domestic and imported silk in important markets of India. The high correlation coefficients of prices between different markets suggested that prices of imported raw silk and domestic silk were moving together irrespective of the location of the markets and source of imports. The results indicated higher correlation between maximum price of filature silk of Bangalore silk exchange and imported silk. To examine lead lag relationship between different markets Granger causality test was conducted. The results showed that Bangalore silk exchange prices for raw silk influenced the Varanasi market China raw silk prices within two weeks. In turn, Varanasi market china raw silk prices influenced the Bangalore market china raw silk prices within a week. It was concluded that there was a definite relationship between the raw silk prices at different markets and it was not instaneous.

Parameshwarappa (1997) employed co integration analysis to examine whether the prices of Indian silk are integrated with the world indicator prices of silk yarn. It was observed that co-integration proves that in the long run there is no relationship between Indian silk yarn and world indicator prices. This is an indication of the domestic prices from that of world prices.

Mahesh (2000) studied the relationship between domestic (Kolkata) and international (London) market prices series of tea using the co-integration analysis. The results revealed that the tendency of the price series of both domestic and international market for tea move in-unison in the long-run confirming the law of one price (LOP).

Jayesh (2001) studied market integration for spices using correlation coefficient. The zero order correlation matrix of prices showed a strong integration among the selected markets of kerala, Karnataka and Tamil nadu for both pepper and cardamom.

Balappa Shivaraya (2002) has made an attempt to examine the extent of price integration of onion and potato in the selected markets of North Karnataka comprising Belgaum, Bijapur, Dharwad, Gulburga, Raichur and Hubli. Zero-order correlation matrix between average wholesale prices of onion clearly indicated the integration among the selected markets, except Bijapur with other markets. However, the magnitude of integration was found to be higher between Belgaum and Raichur (0.9447), between Belgaum and Hubli (0.9253), Raichur and Gulburga (0.8669) and Belgaum and Gulburga (0.8393).

Amitkar et al. (2004) studied marketing infrastructure in Himachal Pradesh and integration of the Indian apple markets. The data was collected from various secondary

sources. Exponential growth model and cuddy Delia valls method and co-integrated methods were employed. The study revealed that Chennai, Delhi and Mumbai markets were well integrated indicating existence of price diplomacy among various market were well integrated indicating existence of price dependency among various markets.

Gangadharappa (2005) conducted a study in Bangalore, Belgaum, kolar, Hassan and Hubli market during 1996-97 to 2003-04. The correlation coefficients were calculated between the arrivals and prices of all the selected markets, which indicated that the coefficients are significant except Bangalore market. All the selected markets are integrated with zero order of integration.

Kerur (2007) computed correlation analysis for market integration of regulated markets in Karnataka. The results showed that before the improvement in Market Information System (MIS), there was integration between Ranebennur and Raichur market. Strong market integration was observed between Gulbarga and Raichur markets for jowar may be due to nearness of the markets.

2.4 Box-Jenkins Model and its Application

A class of ARIMA (Auto Regressive Integrated Moving Average) model is called Box-Jenkins model. Box and Jenkins popularized it during late sixties. The application of these models for predicting prices of agricultural commodities is very few. Some studies which have used this modular, reviewed below.

Leuthold et al. (1970) forecasted daily hog prices and daily quantities supplied by using several alternative techniques. A distinction between econometric and the Box Jenkins models was made. It was stated that the former identified and measured both economic and non-economic variables affecting price and quantity, while the latter identified the stochastic components. The models were tested using Theils ‘U’ coefficient and the authors concluded that the econometric models yielded slightly superior forecasts. Finally, it was concluded that although better forecasts would be obtained by econometric models yet stochastic models were less prone to error and were less expensive.

Schmity and Walts (1970) forecasted wheat yield changes in four largest wheat exporting countries US, Canada, Australia and Argentina using Box Jenkins models. These forecasts were compared with those obtained by exponential smoothing using Theils ‘U’ inequality coefficient and concluded that forecasts with parametric modelling gave better results for the US but not for the others.

Chatfield and Protharo (1973) observed that the Box Jenkins procedure was not suitable for the sale forecasts with a multiplicative seasonal component. In this analysis, monthly data on sales of a company was used. The adequacy of the model was tested using Box-Pierce Test.

Govindan (1974) used Box Jenkins model to analyze wholesale price indices of rice, wheat, jowar and gram. The short term forecasts were found to give good results while the same was not true of long term forecasts. Janus quotients of the forecasts showed that the model gave good results.

Newbold and Granger (1974) compared the forecast performance of the Box-Jenkins, Holt-winters and step-wise regression models. The study indicated that each method had its own advantage over the others. It was opined that the Box-Jenkins gave better forecast in the short–run, but the method required time and skill to compute. The results indicated that for time series with less than 30 observations, step wise regression was better. For data between 30 to 50 observations, a combination of Holt-winters and step wise regression was found suitable. For series of 50 and above the Box-Jenkins performed well. For data with strong seasonal and long fluctuations, the Holt-winters model was suggested.

Protharo and Wallis (1976) examined the extent to which variations in a series could be explained first by a dynamic econometric model and then by ARIMA model. Econometric model clearly indicated that they provided a closer estimate of behaviour of the series during the sample periods.

Chatfield (1977) observed that the Box Jenkins approach being a valuable addition in the forecast tool bag which gave a deeper understanding of time series behaviour. Even though it was found to be more expensive yet the accuracy justified the cost.

Makridakis and Hibbon (1979) averred that accuracy of forecasts are negatively associated with the error term. Several tests to arrive at the accuracy of forecasts like mean square error (MSE), Theils ‘U’ coefficient and mean absolute percentage error (MAPE) were suggested.

Chengappa (1980) applied the Box Jenkins model to forecast poor sale and export auction prices of coffee. Monthly data were used and due to the distinct seasonal variation in prices, the ARIMA seasonal model was applied. The poor sale price forecasts were found to be accurate when compared to forecast of export prices. This was attributed to a possible lack of stationarity of the data. Hence adoption of differencing procedure or a transformation to make the data stationary was found necessary for a better estimate of export prices.

Achoth (1985) analyzed the supply, price and trade of Indian tea by fitting ARIMA models to data on prices and production. The moving average models were found to be most suitable. Among the price series a particular month’s price was not related to the price of the immediate previous month but significantly related to the price of same month in previous years. However, the production in a particular month was related both to production of the previous month as well as to the production of same month in previous years. The forecasts yielded reasonably good results as judged from the tests of their efficiency. The forecasts of prices were superior when compared to the forecasts of quantities, which was attributed to the highly structured pattern of price behaviour.

Achoth (1985) fitted the seasonal ARIMA model to price data of tea at Calcutta and cochin auctions to production data of Northern and Southern regions of the country and quantity of tea exports and their prices. He identified that the moving average model was most suitable. The forecasts from these models yielded reasonably good ex-post and ex-ante forecasts judging from the test of their efficiency. By for the forecast of prices were superior to the forecasts of quantities which may be due to the predictable pattern of price behaviour. Further, some of the models fitted to the quantity series did reveal a certain degree of inadequacy which was not considered serious probably because certain cyclic pattern may not have been captured by the model.

Devaiah et al. (1988) attempted forecasting the prices of cocoons at Ramnagaram market by using ARIMA models. The forecasts were made for 13 months from April 1987 to April 1988. The forecasted values were observed to be close to he actual prices.

Lanciotti (1990) presented a paper that analysis of time series data of monthly prices for a group of diary products with the aim of obtaining reliable forecasts. The method of analysis employed is ARIMA as put forward by Box-Jenkins. The time series data covers both wholesale and retail prices for butter, Gorgonzola, Provolone, Grana Padano and Pasmigiano Reggiano. To estimate the reliability of the forecast obtained, a comparison is made with those resulting from naïve models do not require any estimates. Indicators on the accuracy of the forecasts show that except for Grana Padana, Le ARIMA forecasts are better.

Yin-Runsheng and Mins-Rs (1999) conducted timber price forecasts were univariate Auto Regression Integrated Moving Average (ARIMA) models employing the standard Box-Jenkins modeling strategy by using quarterly price series Timber Mart South. The results showed that most of the selected pipe pulpwood and saw timber markets in six southern US states can be evaluated using ARIMA models, and that short-term forecasts, especially those of one lead forecast, are fairly accurate. It is suggested that forecasting future prices could aid timber producers and consumers alike in timing harvests reducing uncertaining and enhancing efficiency.

Mastny (2001) used ARIMA models, also called Box and Jenkins models after their developers, is a group of models allowing the analysis of the time series with various features. The article demonstrates the possible usage of the Box-Jenkins methodology for the analysis of time series for agricultural commodities. The paper contains a basic mathematical explanation of ARIMA models together with a practical illustration of a price development forecast for a selected agricultural commodity.

Gangadharappa (2005) fitted ARIMA model to study the variation in arrivals and prices of potato in Bangalore, Belgaum, kolar, Hassan and Hubli markets of Karnataka during 1996-97 to 2003-04. Box-Jenkins method was applied for precise forecasting of arrivals and prices of potato for the monthly data to all the selected markets. Of all the ten series, he found only two series, which yielded Box –Pierce ‘Q’ statistic which was significant and AIC was minimum.

Punitha (2007) attempted to fit ARIMA model to forecast the values of arrivals and prices of maize and ground nut for Davengere market and Hubli market. The forecasted values of groundnut arrivals and prices showed an increasing trend in Davangere market, but in Hubli market prices showed decreasing trend. The forecasted values of arrivals and prices of maize showed an increasing trend in both the markets.

Satya et al. (2007) made an attempt to forecast milk production using statistical time series modeling techniques such as double exponential smoothing and Auto- Regressive Moving Average (ARIMA) for the study period of twenty five years (1980-81 to 2004-05). On validation of the forecast from these models, ARIMA model performed better than the other one.

3. METHODOLOGY

The aim of this chapter is to provide a brief description of the materials which provide the necessary data base for the study under the following heads and to highlight the important statistical tools employed.

3.1 Description of the selected markets

3.2 Nature and sources of data

3.3 Analytical tools and techniques

3.1 Description of the selected markets

In Karnataka, there are 56 working cocoon markets, out of these 14 are seed cocoon markets and remaining 42 are reeling cocoon markets. Among the reeling cocoon markets, Ramnagar and Siddlaghatta market are class I markets which have been selected for the present study. A brief description of the selected markets is presented below.

3.1.1 Ramnagar market

The Ramnagar cocoon market is the largest and oldest cocoon market in India. It was strengthened in the year 1984 under World Bank assistance. The market is located 50 km away from Bangalore on Bangalore-Mysore highway. The cocoon supply to this market is from Ramnagar, Mandya, Chitradurga, Tumkur and Bellary. In addition, some quantities of cocoons are brought from the neighbouring states like Andhra pradesh, Tamil nadu, kerala and Maharashtra for transaction. The cocoon transaction is by open auction method. The market is showed in Plate 1.

3.1.2 Siddlaghatta market

The Siddlaghatta cocoon market is second largest cocoon market in Karnataka and it was strengthened in the year 1983 under World Bank assistance. The market is located in kolar district which is 50 km away from Bangalore. The cocoon supply is from Chikballapur, Kolar, Bangalore rural, Chitradurga, Davengere, Haveri, Gadag, Gulburga, Bijapur and also from Andhra Pradesh and Tamil nadu. The market is showed in Plate 2.

3.1.3 Transaction of cocoons

Silk cocoons are being a perishable commodity they should be sold soon after harvesting. The farmer who is a commercial silk cocoon producer will take the produce to the market and display the cocoons in the market yard on the metal bin platform in thin layer. It is showed in Plate 3. The reelers who are the buyers assemble around the cocoon lots and assess the quality of cocoons. Transaction of cocoon is by open auction. The market officer will arrange for auctioning of cocoons and auctioning will be done in his presence. It is displayed in Plate 4. Reelers quote their price and when the price gets stable auctioner gives three calls and closes the bidding with the third and final call in favour of the highest bidder. If the farmer is agreeable to the price, the cocoons will be sold to the highest bidder. Then the cocoons are filled in pre-weighted plastic crates and taken to trolleys to weighing platform for electronic weighment. After weighment the buyer take the possession of cocoons and make the payment at the counter, then the market officer will arrange the payment to the farmer on the same day.

3.2 Database

The data collected for the study were monthly price and arrivals of cocoon from Ramnagar and Siddlaghatta markets for ten years from the available records (i.e.) from 1998-99 to 2007-08. Data on monthly arrivals were recorded in million tonnes and monthly price in Rs/kg.

3.3 Analytical tools and techniques

In this section, a brief description of statistical tools employed has been presented.

Plate.1. Ramnagar cocoon market

Plate.2. Siddlaghatta cocoon market

3.3.1 Analysis of Growth Rates

To compute the average compound growth rates of cocoon arrivals and prices, the following form of regression equation was used

t

t

t uabY = 3.1

Where

tY - Dependent variable for which growth rate was estimated.

a - Intercept

b - Regression coefficient

t - Time period

ut - Disturbance term for the year t.

The equation (3.1) was transformed in to log linear form as follows

ln Y = ln a + t ln b + ln ut

The equation was estimated using ordinary least square technique. The compound growth rate (g) in percentage was then computed from the relationship

g = (Antilog of ln b - 1) x 100

The significance of the regression coefficient was tested using student’s t test.

3.3.2 Time series analysis

Time series analysis was done to study the variations in arrivals and prices of cocoon in monthly prices and arrivals of cocoon for the period of 10 years.

A time series is a complex mixture of four components namely, Trend (T), Seasonal (S), Cyclical (C) and Irregular (I). These four types of movements are frequently found either separately or in combination in a time series. The relationship among these components is assumed to be additive or multiplicative, but the multiplicative model is the most commonly used, which can be represented as

Ot = T x C x S x I

Where,

Ot - Original observation at time‘t’

T - Secular trend

S - Seasonal variations

C - Cyclical movements

I - Irregular fluctuations

Secular trend (T)

Over a long period of time, time series is very likely to show a tendency to increase or decrease over time. The factors responsible for such changes in time series are the growth of population, change in the taste of people, technological advances in the field etc.

There are different types of trends, some of them are linear and some are non-linear in their form. For shorter period of time, in most of the situations the straight line provides the best description of trend and for longer period of time, the non-linear form generally provides a good description of the trend. Often, it may be possible to describe such movements with a structured mathematical model. In the absence of such a definite format, approximately a polynomial or a free hand curve could describe the movements.

Seasonal variation (S): The variation within a year is called as seasonal variation. The main causes of seasonal variations are customs, climates etc. Such seasonal components can be analyzed through harmonic analysis.

Plate.3. Display of cocoons in market yard on metal platform

Plate.4. Market officer in final price bidding

Cyclical movements (C): Cyclical movements are fluctuations which differ from periodic movements. Cyclical movements have longer duration than a year and have periodically of several years as in business cycles.

Irregular variations (I): Here the effects could be completely unpredictable, changing in a random manner. A given observation is affected by episodic and accidental factors. These are also known as causal series and are affected by the unknown causes. These unknown causes act in an unpredictable manner.

3.3.2.1 Estimation of seasonal indices of monthly data

The multiplicative model permits the estimation of each of the four components.

As a first step to estimate the seasonal index, a 12 month centered moving average was calculated as follows.

1 2 3 12 131

Y 2Y 2Y ... 2Y YM

12

+ + + + +=

2 3 4 13 14

2

Y 2Y 2Y ... 2Y YM

12

+ + + + +=

3 4 5 14 153

Y 2Y 2Y ... 2Y YM

12

+ + + + +=

etc., which is a sequential manner for each points of time t.

In this fashion, a 12 month centered moving average removes a large part of fluctuation due to the seasonal effects so that what remains is mainly attributable to other sources viz., long term effects Tt, cyclical effect Ct and the irregular variation It which is due to random causes is also minimized by the process of smoothing out effect. Thus, this affords a means of not only estimating TC effect but also estimating seasonal components.

In the next step of computing the seasonal index, the original series is divided by the centered moving average. This gives the first estimate of seasonal components St.

( )

t

t

tTC

YS =

( )

( )tt

tttt

CT

ISCT

.

...=

It is always expressed in terms of percentages (Column 4 of Table 3.1). In this process, we do not have moving average for the first six and last six months. These seasonal components are next arranged month-wise for each year (Table 3.2)

The last row in the Table 3.2 give estimates of seasonal index for the 12 months adjusted for their total to 1200 or averaged to 100.

The last row in the Table 3.2 gives the first estimates of seasonal variations. In order to obtain a better estimate i.e., stabilized seasonal indices we need to employ an interactive process as under.

The original observation (Yt) is divided by corresponding (St) value and then obtain the residual (TCI)t corresponding to time point t.

( ) ( )t

t

t

t

tS

TCSI

S

YTCI ==

The residual series (TCI)t thus obtained is subjected to the same process of determining 12 month centered averages as done earlier to obtain better estimates for trend cycle effect viz., (TC)t. These revised estimates are next employed as above to generate a revised set of seasonal indices by dividing each observation (Yt) by the corresponding (TC)t value. This will lead to revise estimates of seasonal indices (St) as second interactives ones.

Table 3.1: Computation of centered 12 month moving average

Observations Year / Month

(Y)

Centered 12 month moving average

Percent 12 month moving

average

1998 April Y1 - -

May Y2 - - June Y3 - - July Y4 - - August Y5 - - September Y6 - -

October Y7 M1 S1 December Y8 M2 S2

1999 January Y9 M3 S3 February Y10 M4 S4 March Y11 M5 S5 April Y12 M6 S6 May Y13 M7 S7 June Y14 M8 S8 July Y15 M9 S9 August Y16 M10 S10 September Y17 M11 S11

October Y18 M12 S12 November Y19 M13 S13

December Y20 M14 S14

2000 January Y21 M15 S15

• • • •

• • • • 2008 Y M S

Table 3.2: Average of percentage centered 12 month moving average and computation of seasonal index for observation

Year Apr May Jun July Aug Sep Oct Nov Dec Jan Feb Mar

1998

1999

**

**

2008

Mean

Adj.

Seasonal

Index

*

S

*

*

S

*

*

*

S

*

*

S

*

*

*

S

*

*

S

*

*

*

S

*

*

S

*

*

*

S

*

*

S

*

*

*

S

*

*

S

*

*

S

S

*

*

S

*

*

S

S

*

*

S

*

*

S

S

*

*

S

*

*

S

S

*

*

S

*

*

S

S

*

*

S

*

*

S

S

*

*

S

1200

100

This interactive process is separately employed until stabilized seasonal indices are obtained i.e., two successive seasonal indices do not differ by more than five per cent i.e.

( ) 12,....2,1,5100 ==≤×+

= jiS

SSTCI

i

ji

t

3.3.2.2 Estimation of cyclical indices

The most commonly used method for estimating cyclical movement of time series is the residual method by eliminating the seasonal variation and trend. This is accomplished by dividing (Yt) by corresponding (S) for time‘t’

Symbolically

S

ISCTICT

..... =

These deseasonalized data contain trend, cyclical and irregular components. This trend cycle components are plotted against time for examining cyclical behaviour. If there is any existence of cycle, periodicity of cycle is noted. Again moving average of length equal to periodicity of cycle is computed for eliminating cyclical behaviour.

These moving averages are arranged cycle wise. These are adjusted for cyclical indices, as in the case of seasonal indices. Then trend cycle values (TC) are divided by adjusted components CI.

The examination of both the graphs of trend cycle component as well as trend component will give a clear idea of the presence of cycle.

If there is similarity in these two graphs, it is an indication of non-existence of the cycle. However, the non-similarity in the two graphs is an indication of the presence of the cycle. If ultimately a cycle is reflected, then the cyclical effect is removed from T-C components. If no cycle is detected, then the trend cycle values are treated as pure trend values. The Friedman’s two way analysis of variance was employed to know the significant difference among months within a cycle and also between cycles. A significant difference indicates the presence of changing cyclical behaviour and non-significant difference indicates the consistency of cyclical pattern.

Table 3.3: Tabular format of obtaining cyclical component

Months Cycle

1

2

3

31

32

60

Total

I

II

III

IV

V

*

C

C

C

C

*

C

C

C

C

*…………...*

C…………..C

C…………..C

C…………..C

C…………..C

C

C

C

C

C

C…………..C

C…………..C

C…………..C

C…………..C

C…………..C

C

C

C

C

C

Mean

Cyclical

index

(adjusted)

-

-

-

-

-

-

-

-

(Row

total

6000)

3.3.2.3 Analysis of long-term movements

The residuals (Tt = Yt/StCt) after eliminating seasonal effects and cyclical effects (if any) from original observations (Yt) are used to determine the trend. If there is no cyclical pattern, then trend cycle components are treated as trend values.

When definite mathematical model cannot be identified to fit the trend data, the orthogonal polynomial model are used to determine the long term behaviour. These models are fitted by the principles of Least Squares. The polynomial model tried is shown below.

1st degree (straight line) : ubxaYt ++=

2nd

degree polynomial : ucxbxaYt +++= 2

3rd

degree polynomial : udxcxbxaYt ++++= 32

4th

degree polynomial : uexdxcxbxaYt +++++= 432

5th

degree polynomial : ufxexdxcxbxaYt ++++++= 5432

6th

degree polynomial : ugxfxexdxcxbxaYt +++++++= 65432

Where,

Yt = Trend values at time t

u = Disturbance term

a, b, c, d, e, f and g = the coefficient to be estimated

The suitable model for data is judged based on R² (coefficient of determination) value.

3.3.3 Relationship between two markets

The most convenient and simple method for measuring the relationship between two markets is conventionally through computation of correlation coefficient between unadjusted series of two markets. However, while correlating price series of two markets, of a given

period, it is necessary to adjust for trend, otherwise there will be a biased measure of market integration, because price contains trend effects also. Therefore, price series adjusted for trend is recommended as a better measure.

The correlation coefficient technique was adopted to assess the nature and magnitude of association between arrivals and prices of cocoon in the Ramnagar and siddlaghatta markets. The coefficient of correlation ‘r’ was calculated using the following equation.

∑xy - ∑x ∑y n

r = ——————————————

[∑x² - (∑x)²] [∑y² - (∑y)²]

n n

Where,

r = Correlation coefficient

x = Prices of cocoon in selected markets

y = Arrivals of cocoon in selected markets

n = Number of observations

The significance can be tested by‘t’ test with n-2 degrees of freedom

3.3.3.1 Concurrent deviation method

Concurrent deviation method used for time series data, gives idea about short term fluctuation in variables. It is used to find whether both variables are moving in same direction or not.

n

ncrcd

−±±=

2

c = concurrent deviate (The deviate is calculated in both the variables move in the same direction)

n = N-1

Where n = total number of observations

3.3.4 Box-Jenkins models

The Box-Jenkins procedure is concerned with fitting a mixed Auto Regressive Integrated Moving Average (ARIMA) model to a given set of data. The main objective in fitting this ARIMA model is to identify the stochastic process of the time series and predict the future values accurately. These methods have also been useful in many types of situation which involve the building of models for discrete time series and dynamic systems. But, this method was not good for lead times or for seasonal series with a large random component (Granger and Newbold, 1970).

Originally ARIMA models have been studied extensively by George Box and Gwilym Jenkins during 1968 and their names have frequently been used synonymously with general ARIMA process applied to time series analysis, forecasting and control. However, the optimal forecast of future values of a time-series are determined by the stochastic model for that series. A stochastic process is either stationary or non-stationary. The first thing to note is that most time series are non-stationary and the ARIMA model refer only to a stationary time

√

21

2

r

nrt

−

−=

series. Therefore, it is necessary to have a distinction between the original non-stationarity time series and its stationarity counterpart.

3.3.4.1 Stationarity and non-stationarity

The term stationarity meaning that the process generating the data is in equilibrium around a constant value and that the variance around the mean remains constant over time. The data must be roughly horizontal along time axis.

If mean changes over time (with some trend cycle pattern) and variance is not reasonably constant then series is non-stationary in both mean and variance.

If a time series is not stationary, then it can be made more nearly stationary by taking the first difference of the series. Conversely a stationary process may be summed or integrated to give a non-stationary process.

Let Xt be a random variable and xt (where t=1, 2, . . . n) be the observations on Xt with density function f (xt). If the observations are independent, then

( ) ( ) ( ) ( )nnn xfxfxfXXXf .............., 221121 =

This implies that joint distribution is independent of historical time.

The assumption of stationarity reduces the number of parameters in the joint probability density function of a random variable xt in the series.

Since the ARIMA models refer only to a stationary time series, the first stage of Box-Jenkins model is reducing non-stationary series xt to a stationary series Yt by taking first differences as follows.

tt XY ∆=

1−−= tt XX

tt BXX −=

( ) tXB−= 1 3.2

Where,

B = Backward shift operator

The backward shift operator is convenient for describing the process of differencing. To define B, such that

1−= tti XXB i= 1, 2,. . .

Suppose the first difference of the series doesn’t become stationary then second order differencing is done as follows

( )tt XY ∆∆= 3.3

( )1−−∆= tt XX

( ) ( )211 −−− −−−= tttt XXXX

212 −− +−= ttt XXX

ttt XBBXX22 +−=

( ) tXBB221 +−=

tXB2)1( −=

In general, if it takes a dth order difference to achieve stationarity we will write.

dth order difference ( ) t

dXB−= 1 3.4

The general ARIMA (o, d, o) model will be

( ) tt eXB =− 21 3.5

Where et is error term distributed normally with

( ) ( ) 2,0 ttt eeVeE == and

( ) =ji eeCov , θ for all t (i ≠ j)

In order to test the stationarity, compute the auto-correlation functions (ACF) of difference series (Yt) up to 24 lags. If the ACF for first and higher differences (after 2-3 lags) drop abruptly to zero then it indicates the series is stationary.

3.3.4.2 Stationary time series model

3.3.4.2.1 Auto regressive process (p, o, o)

If the observation Yt depends on previous observation and error term et is called auto regressive process (AR process)

Yt = µ + ∅tYt-1 + ∅2Yt-2 + . .. . . + ∅pYt-p + et

= ∅p (B) (Yt-µ) + et 3.6

Note the term µ in equation (3.5) is not quite the same as the “Mean” of the Y series. Rather, the development is as follows.

( ) ( ) ttpt eYY +−=− µφµ

( ) ( ) ( )tptptt eYYY +−++−+−= −−− µφµφµφ ....2211 3.7

tptptt eYYY +−++−+−= −−− )(...)()( 2211 µφµφµφ

tptptpt eYYY ++++−−−= −− φφµφµφµ ...)...( 111

tptpt eYY ++++= −− φφµ ...111

3.3.4.2.2 Moving average process (o, o, q)

If the observation Yt depends on the error term et and also on one or more previous error terms (et’s) then we have moving average (MA) process.

t t 1 (t 1) 2 ( t 2) q (t q)Y e e e ... e− − −= µ + − θ − θ − θ 3.8

Where,

θi = ith moving average parameter

i = 1, 2, . . . . q

q = Order moving average

3.3.4.2.3 Mixtures : ARIMA process

If the non-stationarity is added to a mixed ARIMA process, then the general ARIMA (p, d, q) is implied. Here the word integrated is confusing to many and refers to the differencing of the data series.

( ) ( ) ( ) t

q

pt

p

p

deBYBB φµφ −+=−− 111 3.9

Seasonality and ARIMA models

Some time series exhibit perceptible periodic pattern for instance price and arrivals of Agricultural commodities usually have a seasonal pattern process then the general.

The ARIMA notation can be extended readily to handle seasonal aspects and the general shorthand rotation is ARIMA

(p.d.q.) (P.D.Q.)s

(non-seasonal (Seasonal part

part of the model) of the model)

s = number of periods per season

The mixture of AR and MA seasonal model is

∅p (B) ∆d ∅p(Bs) ∆D

xt = θq (B) . (H)Q (Bs) et 3.10

If Yt = ∆d∆d xt the model becomes an integrated model.

s

The main stages in setting up a Box-Jenkins forecasting model are as follows.

1. Identification

2. Estimating the parameters

3. Diagnostic checking and

4. Forecasting

3.3.4.2.4 Identification of models

A good starting point for time series analysis is a graphical plot of the data. It helps to identify the presence of trends.

Before estimating the parameter (p, q) of model, the data are not examined to decide about the model which best explains the data. This is done by examining the sample ACF (Autocorrelation function) and PACF (Partial Autocorrelation function) of differenced series Yt.

The sample auto correlations for k time lags can be found and denoted by rk as follows.

( ) ( )tkt YrY =ρ̂ 3.11

( )( )t

tk

YC

YC

0

=

where,

( ) ( )( )YYYYn

YCkt

kn

t

ttk−−= +

−

=∑

1

1

K = 0, 1, 2, . . . . n

t = 1, 2, . . . n-k

∑=

=n

t

tt Yn

Y1

1

n = Length of time period

Both ACF and PACF are used as the aid in the identification of appropriate models. There are several ways of determining the order type of process, but still there was no exact procedure for identifying the model.

3.3.4.2.5 Estimation of parameters

After tentatively identifying the suitable model, next step is to obtain Least Square Estimates of the parameters such that the error sum of squares is minimum.

n2

t

t 1

S( , ) e ( , )=

θ ∅ = θ ∅∑ 3.12

where,

t = 1, 2, 3 . . . n

There are fundamentally two ways of getting estimates for such parameters.

a) Trail and error: Examine many different values and choose set of values that minimizes the sum of squares residual

b) Interactive method: Choose a preliminary estimate and let a computer programme refine the estimate interactively.

The latter method is used in our analysis for estimating the parameters.

3.3.4.2.6 Diagnostic checking

After having estimated the parameters of a tentatively identified ARIMA model, it is necessary to do diagnostic checking to verify that the model is adequate.

Examining ACF and PACF of residuals may show an adequacy or inadequacy of the model. If it shows random residuals, then it indicates that the tentatively identified model was adequate. When an inadequacy is detected, the checks should give an indication of how the model be modified, after which further fitting and checking takes place.

One of the procedures for diagnostic checking mentioned by Box-Jenkins is called over fitting i.e. using more parameters than necessary. But the main difficulty in the correct identification is not getting enough clues from the ACF because of inappropriate level of differencing. The residuals of ACF and PACF considered random when all their ACF were within the limits.

)12(196.1 −±

n 3.13

Box and Pierce ‘Q’ statistic was used to check whether the auto correlations for these residuals are significantly different from zero. It can be computed as follows.

∑=

=m

k

krnQ1

2 3.14

where,

m = Maximum lag considered

n = N – D

N = Total number of observations

rk = ACF for lag k

D = Differencing

And Q is distributed approximately as a Chi-square statistic with (m-p-q) degree of freedom.

The minimum Akike Information Coefficient (AIC) criterion is used to determine both the differencing order (d, D) required to attain stationarity and the appropriate number of AR and MA parameters, it can be computed as follows.

( ) { }mnAIC qp 2log)2log1( 2 +++=+ σπ 3.15

Where,

2σ = Estimated MSE

n = Number of observations

m = p + q + P + Q

This diagnostic checking helps us to identify the differences in the model, so that the model could be subjected to modification, if need be.

3.3.4.2.7 Forecasting

After satisfying about the adequacy of the fitted model, it can be used for forecasting. Forecasts based on the model.

s s

t t(1 B)(1 B) Y (1 B)(1 (H) B)e− ∅ − φ = − θ − 3.16

were computed for upto 36 months (m) ahead. The above model (3.16) gives the forecasting equation is

t t 1 t 12 t 13 t t 1 t 12 t 13Y Y Y Y e e (H)e (H)e− − − − − −= ∅ + φ − ∅φ + − θ − + θ 3.17

Given data upto time‘t’ the optional forecast of Y (also called Ex-Ante forecast) model at the time t is the conditional expectation of Yt+1.

It follows, in particular, that

1−−= ttt YYe 3.18

The errors et in model (3.18) are in fact that forecast errors for unit lead time. That for an optimal forecast these ‘one step ahead’ forecast errors ought to form an uncorrelated series is otherwise obvious. Suppose, if these forecast errors were autocorrelated, then it could be possible to forecast the next forecast error in which case it could not be optimal.

The required expectations are easily found because

( ) ( ) ( ) 0, == ++ mttmt eEmYYE 3.19

Where,

m = 1, 2, 3 . . . . . n

( ) ( ) 1−−−−−−− −=== mtmtmtmtmtmt YYaeEYYE 3.20

Where, m = 0, 1, 2 . . . n

For instance, to determine the three month ahead (1-3) forecast for series Yt (use equation 3.17).

Yt+1 = Yt+3

t 2 t 9 t 10 t 13 t 2 t 9 t 10Y Y Y e e (H)e (H)e+ − − + − − −= ∅ + φ − ∅φ + − θ − + θ

taking conditional expectations at time t,

Yt (1) = Yt (3)

t (2) t 9 t 10 t 9 t 10 t 10 t 11Y Y Y 0 (0) (H)(Y Y ) (H)(Y Y )− − − − − −= ∅ + φ − ∅φ + − θ − − + θ −

Because, 1111)1ˆ)(,0( −−−−+ =−== ttttt eYYeEeE

i.e. Yt (3) = 0 Yt (2)

The forecast Yt (2) can be obtained in a similar way in terms of Yt (1) from E (Yt+2). Similarly Yt (1) can be obtained from E (Yt+1).

In practice it is very easy to compute the forecast Yt (1), Yt (2), Yt (3) etc. recursively using the forecast function (3.19).

t 1 t 1 t 1 t 1 t 1 t 1 t 1E(Y ) E(Y 1 Q e 1) e 1 (H)e 12 (H)e 13+ + + + + + += − + − − − θ − − − + θ − and

using 3.18 and 3.19.

However, using these methods, Ex-post forecasts can also be calculated for comparing with the value actually realized.

The accuracy of forecasts for both Ex-ante and Ex-post were tested using the following tests (Markidakis and Hibbon, 1979).

1) Mean square error (MSE); the formula for computing MSE is

2

1

)ˆ(n

1 MSE tt

n

t

XX −= ∑=

Where,

Xt = Actual values

tX̂ = Predicted values

2) Mean average percentage error (MAPE): The formula for this is

100)ˆ(

n

1 MAPE

2

1

×−

= ∑= t

ttn

t X

XX

Where,

Xt = Actual values

tX̂ = Predicted values

4. RESULTS

Keeping in view of the specific objectives of the present study, the data collected on the arrivals and prices of cocoon in Ramnagar and Siddlaghatta market have been subjected to various statistical methods as outlined in the materials and methods. The results are reported in this chapter under the following headings.

4.1 Growth pattern in arrivals and prices of cocoon

4.2 Behaviour of arrivals and prices of cocoon

4.3 Market integration

4.4 Forecasting of arrivals and prices

4.1 Growth pattern in arrivals and prices of cocoon

Detailed analysis of growth pattern in arrivals and prices of cocoon in study markets is presented as under

4.1.1 Growth pattern in arrivals and prices of cocoon in Ramnagar market

The total arrivals in cocoon have reached about 11,034.94 million tonnes during the year 2007-08, with a significant compound growth rate of 0.058. But the value of cocoon recorded a negative compound growth rate of -0.007 (Table 4.1).

4.1.2 Growth pattern in arrivals and prices of cocoon in Siddlaghatta market

The total arrivals in cocoon have reached about 14,389.84 million tonnes during 2007-08, with a significant compound growth rate of 0.141. But the value of cocoon recorded a negative compound growth rate of -0.017 (Table 4.1).

4.2 Behaviour of arrivals and prices of cocoon

4.2.1 Seasonal indices of cocoon arrivals and prices in selected markets

Seasonal indices of market arrivals and prices of cocoon in Ramnagar and Siddlaghatta markets are presented in Table 4.2

4.2.1.1 Seasonal indices of cocoon arrivals and prices in Ramnagar market

The seasonal indices of arrivals and prices of cocoon in Ramnagar market are presented in the Table 4.2 and Fig 4.1 and Fig 4.2. The highest arrivals indices are noticed in the month of March (139.00) and November (104.19). The lowest arrivals are obtained in the month of August (84.63) and April (91.45). As far as the price indices of cocoon are concerned, the highest price indices are observed in the month of February (109.53) and January (106.38). The lowest indices are recorded in the month of October (90.84) and September (95.96) respectively.

4.2.1.2 Seasonal indices of cocoon arrivals and prices in Siddlaghatta market

The seasonal indices of arrivals and prices of cocoon in Siddlaghatta market have been presented in Table 4.2 and Fig 4.1 and Fig 4.2. The highest arrivals indices are observed in the month of March (125.74) and November (105.72). The lowest arrivals are recorded in the month of April (84.97) and June (85.69). As far as the price indices of cocoon are concerned, the highest price indices are noticed in the month of April (110.23) and June (110.10). The lowest indices are obtained in the month of November (86.23) and October (86.97) respectively.

4.2.2 Secular trend in arrivals and prices of cocoon in selected markets

4.2.2.1 Secular trend in arrivals of cocoon in Ramnagar market

In order to determine the nature of trend movement in the arrivals of cocoon in Ramnagar market, the data is fitted to sixth degree polynomial equation. The multiple coefficient of determination (R²) value obtained is 69 per cent. The trend equation is in the form of

Table 4.1: Growth rates in arrivals and prices of cocoon from Ramnagar and Siddlaghatta market

Description Compound Growth Rate (%)

Ramnagar Arrivals 0.058* Prices -0.007

Siddlaghatta Arrivals 0.141* Prices -0.017

* Significant at 5% level

Table 4.2: Seasonal indices of monthly arrivals and prices of cocoon in Ramnagar and Siddlaghatta market

Ramnagar market Siddlaghatta market Months

Arrivals Prices Arrivals Prices

April 91.45 100.15 84.97 110.23

May 94.72 97.52 95.82 107.11

June 94.12 98.98 85.69 110.10

July 99.75 97.51 104.03 107.02

August 84.63 101.73 98.86 106.30

September 103.95 95.9 6 104.38 102.99

October 98.84 90.84 105.39 86.97

November 104.19 97.32 105.72 86.23

December 100.67 105.06 96.04 91.29

January 92.72 106.38 98.77 96.92

February 95.96 109.59 94.58 99.51

March 139.00 98.95 125.74 95.32

Total 1199.99 1200.00 1200.00 1200.00

Fig.4.1 seasonal indices of arrivals in Ramnagar and siddlaghatta market

Fig.4.2 Seasonal indices of prices in Ramnagar and Siddlaghatta market

Y = 158.91-21.208x+13.507x2+3.8724x

3 + 0.5411x

4- 0.0361x

5+ 0.009x

6

Where,

Y = Predicted value of trend at time x

X = Years x=0, 1, 2 . . . . . . . n

It could be seen from the above equation that the arrivals of cocoon displayed shows an increasing trend over the years. The graph of the trend in arrivals over the years is shown in Fig. 4.3.

4.2.2.2 Secular trend in prices of cocoon in Ramnagar market

In order to determine the nature of trend movement in the prices of cocoon in Ramnagar market, the data is fitted to sixth degree polynomial equation. The multiple coefficient of determination (R²) value obtained is 92 per cent. The trend equation is in the form of

Y = 19.503 + 1.3279x -0.8039x2+ 0.1949x

3- 0.0223x

4+0.0012x

5-3E-05x

6

Where,

Y = Predicted value of trend at time x

X = Years where x = 0, 1, 2. .... . n

The price of cocoon displayed trend equation with ups and downs over the years. The graph of the trend in prices over the years is shown in Fig. 4.4.

4.2.2.3 Secular trend in arrivals of cocoon in Siddlaghatta market

In order to determine the nature of trend movement in the arrivals of cocoon in Siddlaghatta market, the data is fitted to sixth degree polynomial equation. The multiple coefficient of determination (R²) value obtained is 69 per cent. The trend equation is in the form of

Y = 177.04 - 29.074x+17.688x2- 4.624x

3+0.5859x

4-0.0357x

5+ 0.0008x

6

Where,

Y = Predicted value of trend at time x

X = Years, x = 0, 1, 2 . . . . . . n

It could be seen from the above that, the arrivals of cocoon showed an increasing trend over the years. The graph of the trend in arrivals over the years is shown in Fig.4.5.

4.2.2.4 Secular trend in prices of cocoon in Siddlaghatta market

In order to determine the nature of trend movement in the prices of cocoon in Siddlaghatta market, the data is fitted to sixth degree polynomial equation. The multiple coefficient of determination value obtained is (R²) 77 per cent. The trend equation is in the form of

Y = 22.456 – 2.7678x +1.4639x2 – 0.3097x

3+ 0.0259x

4– 0.0006x

5-8E-06x

6

Where,

Y = Predicted value of trend at time x

X = Years, x = 0, 1, 2 . . . . . . n

The price of cocoon displayed a trend equation with ups and downs over the years. The graph of the trend in the prices of cocoon over the years is shown in Fig. 4.6.

4.2.3 Cyclical trend in arrivals and prices of cocoon in selected markets

The cyclical trend in arrivals and prices of cocoon are presented from Fig. 4.7 and Fig 4.8. It could be seen from the figure that there is no cycles in arrivals and prices of cocoon in both Ramnagar and Siddlaghatta markets.

Fig.4.3 Trend component of arrivals of cocoon in Ramnagar market

Fig.4.4 Trend component of prices of cocoon in Ramnagar market

Fig.4.5 Trend component of arrivals of cocoon in Siddlaghatta market

Fig.4.6 Trend component of prices of cocoon in Siddlaghatta market

Fig.4.7. Cyclical trend of arrivals in Ramnagar and Siddlaghatta markets

Fig.4.8 Cyclical trend of prices in Ramnagar and Siddlaghatta markets

4.3 Market integration

4.3.1Correlation between arrivals and prices of cocoon in selected markets

The correlation coefficients are computed to ascertain the pattern of association between market arrivals and prices of cocoon in selected markets.

The correlation coefficient between arrivals and prices of cocoon in Ramnagar and Siddlaghatta market during the study period are presented in Table 4.3 and 4.4. The year wise correlation between arrival and price in both markets are provided in Table 3.3. It indicates all the years have negative correlation in both markets. The correlation for ten years (120 months) is provided in Table 4.4. It shows that there is a negative and non-significant relationship between the arrivals and prices of cocoon in Ramnagar market. But in case of Siddlaghatta market, the correlation coefficient is negative but significant indicating that the increase in arrivals of cocoon results in decrease in the price.

4.3.2 Concurrent deviation between Ramnagar and Siddlaghatta market

Concurrent deviation is computed to know about short term fluctuation in arrivals and prices. It also helps to find whether both variables are moving in same direction or not. The Table 4.5 indicates that there is a positive relationship between the arrivals of Ramnagar and Siddlaghatta market. Similarly there is a positive relationship between prices of Ramnagar and Siddlaghatta market.

4.4 Forecasting of arrivals and prices

As Box-Jenkins model is preferred to the multiplicative time series model for forecasting purposes. It is used for forecasting of arrivals and prices of cocoon in the selected markets. The results are presented below.

4.4.1 Arrivals and prices of cocoon in Ramnagar market

The detailed analysis of forecasting of arrivals and prices of cocoon in Ramnagar market has been presented as under.

4.4.1.1 Identification of the model

The tentative models are first identified based on the Auto Correlation Function (ACF) and Partial Auto Correlation Function (PACF) for the different series Yt for selected markets. The computed value of ACF and PACF of Ramnagar market are shown in Table 4.6 up to 30 lags. An examination of the ACF and PACF revealed seasonality. However, the series is found to be stationary, since the coefficient dropped to zero after the first or second lag. Each individual coefficient of ACF and PACF are tested for their significance using‘t’ test. Further, the absence of peak at first values clearly indicate suitability of the choice of non-seasonal difference d=1, to accomplish stationarity series. Hence, based on ACF and PACF many models are tried, finally model (1,1,3) (1,1,1) is tentatively identified for arrivals and model (0,1,0) (1,1,1) is identified for prices of cocoon in Ramnagar market.

4.4.1.2 Estimation of parameters

After identifying the models tentatively the next step is to obtain the estimates by the

method of Least Squares Estimates of the parameters φ and θ for both the markets. Such that the error sum of square is to be minimum.

i.e. S(φ . θ) = et² (φ . θ)

The parameters of the tentatively identified models are estimated by an iterative process and then the residual of each of the models is to be estimated.

4.4.1.3 Diagnostic checking

Residual analysis is carried out to check the adequacy of the models. The residuals of ACF and PACF are obtained from the tentatively identified model. The adequacy of the model is judged based on the values of Box-Pierce Q statistics and AIC (Beenstock and Bansali, 1981). The values of the statistics are shown in Table 4.7. The model (1,1,1) (2,1,1)

is found to be the best model for arrivals and for prices, the model (0,1,0) (1,1,1) is found to be the best as it had the lowest estimate for AIC and Q statistics.

Table 4.3: Correlation coefficient between quantity and price in Ramnagar and Siddlaghatta

market (year wise)

Year Ramnagar Siddlaghatta

1998-1999 -0.407 -0.255

1999-2000 -0.413 -0.332

2000-2001 -0.404 0.067

2001-2002 -0.649* -0.546

2002-2003 -0.181 -0.388

2003-2004 -0.123 -0.020

2004-2005 -0.512 -0.704*

2005-2006 -0.221 -0.054

2006-2007 -0.662* -0.621*

2007-2008 -0.339 -0.726**

* Correlation is significant at the 0.05 level

** Correlation is significant at the 0.01 level

NS – non-significant

Table 4.4: Correlation between arrivals and prices of cocoon in Ramnagar and Siddlaghatta

market (120 months)

Market Correlation

Ramnagar -0.116 NS

Siddlaghatta -0.197*

* Correlation is significant at the 0.05 level

NS – non-significant

Table 4.5: Concurrent deviation between Ramnagar and Siddlaghatta market

Variables Values

Arrivals 0.615

Prices 0.557

Table 4.6: ACF and PACF of monthly arrivals and prices of cocoon in Ramnagar market.

Arrivals Prices

Lags ACF PACF ACF PACF

1 -0.054 -0.054 -0.039 -0.039

2 0.092 0.090 -0.086 -0.088

3 -0.047 -0.038 -0.031 -0.039

4 -0.160 -0.175 -0.097 -0.109

5 0.008 -0.001 -0.120 -0.139

6 -0.009 0.023 0.083 0.050

7 -0.234 -0.261 -0.117 -0.150

8 0.142 0.099 0.125 0.109

9 -0.021 0.048 0.002 -0.039

10 0.104 0.050 0.030 0.044

11 0.024 -0.042 -0.123 -0.134

12 0.049 0.096 -0.007 -0.022

13 0.064 0.089 0.006 0.023

14 -0.125 -0.200 -0.030 -0.080

15 -0.043 -0.002 -0.012 0.005

16 -0.065 0.000 0.060 -0.014

17 -0.107 -0.097 -0.208 -0.200

18 0.066 -0.015 0.027 -0.030

19 -0.053 0.010 -0.063 -0.121

20 -0.104 -0.148 -0.058 -0.081

21 0.251 0.165 0.041 -0.045

22 -0.083 -0.020 0.074 -0.019

23 0.124 0.027 0.142 0.167

24 -0.064 -0.091 -0.001 -0.096

25 -0.163 -0.092 -0.210 -0.167

26 0.006 0.004 0.070 0.047

27 -0.001 0.004 -0.052 -0.068

28 -0.136 -0.087 -0.009 -0.028

29 0.099 0.016 0.079 -0.009

30 -0.081 -0.005 -0.017 -0.045

Table 4.7: Residual analysis of Ramnagar and Siddlaghatta market

Market Model AIC Box Pierce Q statistic

Ramnagar

Arrivals (1.1.3) (1.1.1) 546.40 20.23

Prices (0.1.0) (1.1.1) 424.23 16.31

Siddlaghatta

Arrivals (2.1.1) (1.1.1) 561.11 9.74

Prices (0.1.0) (1.1.1) 426.59 15.67

Table 4.8: Actual and Forecasted values for arrivals of cocoon in Ramnagar market

Sl. No. Months

Actual value

Forecasted value Sl. No. Months

Actual value

Forecasted value

1 Apr-98 644.94 . 40 Jul-01 786.07 897.16

2 May-98 675.06 . 41 Aug-01 751.31 622.58

3 Jun-98 685.52 . 42 Sep-01 833.47 910.8

4 Jul-98 1134.58 . 43 Oct-01 791.67 784.39

5 Aug-98 863.24 . 44 Nov-01 935.57 835.02

6 Sep-98 957.81 . 45 Dec-01 597.48 1051.65

7 Oct-98 909.7 . 46 Jan-02 926.39 619.13

8 Nov-98 837.74 . 47 Feb-02 1149.1 999.17

9 Dec-98 1021.71 . 48 Mar-02 1597.09 1461.32

10 Jan-99 974.3 . 49 Apr-02 1012.88 921.79

11 Feb-99 941.03 . 50 May-02 902.08 947.46

12 Mar-99 1667.57 . 51 Jun-02 818.26 1004.34

13 Apr-99 755.23 . 52 Jul-02 917.59 833.63

14 May-99 770.94 784.73 53 Aug-02 633.46 789.73

15 Jun-99 1056.97 784.66 54 Sep-02 729.71 796.66

16 Jul-99 797.06 1409 55 Oct-02 752.66 808.93

17 Aug-99 609.16 715.46 56 Nov-02 959.41 779.03

18 Sep-99 801.3 891.77 57 Dec-02 976.03 971.34

19 Oct-99 647.73 765.15 58 Jan-03 562.06 889.34

20 Nov-99 828.02 674.15 59 Feb-03 665.07 844.53

21 Dec-99 1015.48 946.29 60 Mar-03 866.48 1272.42

22 Jan-00 664.35 913.17 61 Apr-03 561.5 427.61

23 Feb-00 889.43 728.77 62 May-03 593.49 611.1

24 Mar-00 1149.27 1582.33 63 Jun-03 416.41 554.96

25 Apr-00 822.02 360.74 64 Jul-03 604.11 505.32

26 May-00 879.31 794.63 65 Aug-03 696.02 382.55

27 Jun-00 806.11 858.3 66 Sep-03 890.6 704.86

28 Jul-00 729.3 975.37 67 Oct-03 802.6 710.49

29 Aug-00 501.94 558.97 68 Nov-03 923.1 844.47

30 Sep-00 788.92 762.27 69 Dec-03 824.16 847.95

31 Oct-00 860.11 642.59 70 Jan-04 769.18 752

32 Nov-00 779.88 850.4 71 Feb-04 650.95 877.58

33 Dec-00 922.28 915.88 72 Mar-04 918.81 1144.47

34 Jan-01 944.77 774.48 73 Apr-04 551.08 517.59

35 Feb-01 922.96 937.23 74 May-04 756.18 580.3

36 Mar-01 1524.93 1395.38 75 Jun-04 833.9 637.37

37 Apr-01 766.36 824.08 76 Jul-04 806.48 768.75

38 May-01 847.21 802.61 77 Aug-04 798.33 622.59

39 Jun-01 894.59 927.75 78 Sep-04 905.75 883.62

Table 4.8: Contd..

Sl. No.

Months Actual value

Forecasted value

Sl. No.

Months Actual value

Forecasted value

79 Oct-04 887.03 806.2 118 Jan-08 763.98 761.05

80 Nov-04 959.72 986.09 119 Feb-08 835.15 790.95

81 Dec-04 746.86 895.25 120 Mar-08 1135.21 1135.41

82 Jan-05 770.59 733.99 121 Apr-08 . 853.26

83 Feb-05 754.53 829.21 122 May-08 . 841.1

84 Mar-05 1036.32 1130.47 123 Jun-08 . 822.44

85 Apr-05 867.38 611.81 124 Jul-08 . 983.49

86 May-05 856.79 846.82 125 Aug-08 . 811.01

87 Jun-05 879.54 750.66 126 Sep-08 . 931.45

88 Jul-05 1013.95 907.2 127 Oct-08 . 881.44

89 Aug-05 903.11 829.25 128 Nov-08 . 898.36

90 Sep-05 995.86 1027.04 129 Dec-08 . 823.68

91 Oct-05 948.46 928.14 130 Jan-09 . 779.85

92 Nov-05 838.69 1078.28 131 Feb-09 . 775.6

93 Dec-05 807.57 809.5 132 Mar-09 . 1099.61

94 Jan-06 819.47 839.62 133 Apr-09 . 816.37

95 Feb-06 871.96 795.18 134 May-09 . 811.04

96 Mar-06 1368.22 1223.7 135 Jun-09 . 778.13

97 Apr-06 1146.19 856.75 136 Jul-09 . 956.41

98 May-06 1112.06 1093.98 137 Aug-09 . 770.6

99 Jun-06 1068.6 994.09 138 Sep-09 . 900.22

100 Jul-06 1343.43 1149.42 139 Oct-09 . 831.86

101 Aug-06 1036.39 1125.28 140 Nov-09 . 845.06

102 Sep-06 1137.98 1182.97 141 Dec-09 . 772.32

103 Oct-06 1190.04 1128.49 142 Jan-10 . 731.7

104 Nov-06 1291.21 1227.94 143 Feb-10 . 731.22

105 Dec-06 1138.29 1160.55 144 Mar-10 . 1054.31

106 Jan-07 1084.69 1100.64 145 Apr-10 . 768.91

107 Feb-07 930.3 1118.44 146 May-10 . 763.67

108 Mar-07 1184.28 1368.47 147 Jun-10 . 730.17

109 Apr-07 964.39 973.55 148 Jul-10 . 907.25

110 May-07 935.83 1025.48 149 Aug-10 . 721.09

111 Jun-07 849.89 954.27 150 Sep-10 . 849.95

112 Jul-07 1140.16 1036.12 151 Oct-10 . 781.91

113 Aug-07 887.49 980.34 152 Nov-10 . 795.28

114 Sep-07 1065.54 1003.64 153 Dec-10 . 721.25

115 Oct-07 861.05 1070.2 154 Jan-11 . 680.06

116 Nov-07 803.56 936.17 155 Feb-11 . 678.24

117 Dec-07 792.69 850.04 156 Mar-11 . 1001.02

Table 4.9: Actual and Forecasted values for prices of cocoon in Ramnagar market

Sl. No.

Months Actual value

Forecasted value

Sl. No.

Months Actual value

Forecasted value

1 Apr-98 132 . 40 Jul-01 140 132.98

2 May-98 136 . 41 Aug-01 140 143.99

3 Jun-98 142 . 42 Sep-01 123 142.3

4 Jul-98 123 . 43 Oct-01 108 110.92

5 Aug-98 110 . 44 Nov-01 122 127.1

6 Sep-98 123 . 45 Dec-01 139 122.03

7 Oct-98 112 . 46 Jan-02 127 135.17

8 Nov-98 125 . 47 Feb-02 116 127.31

9 Dec-98 137 . 48 Mar-02 108 98.95

10 Jan-99 131 . 49 Apr-02 108 114.35

11 Feb-99 131 . 50 May-02 95 112.41

12 Mar-99 118 . 51 Jun-02 90 94.69

13 Apr-99 119 . 52 Jul-02 95 89.02

14 May-99 117 122.97 53 Aug-02 91 97.58

15 Jun-99 107 122.97 54 Sep-02 88 87.46

16 Jul-99 115 87.97 55 Oct-02 86 75

17 Aug-99 124 101.97 56 Nov-02 85 103.29

18 Sep-99 120 136.97 57 Dec-02 78 90.28

19 Oct-99 107 108.97 58 Jan-03 100 71.78

20 Nov-99 116 119.97 59 Feb-03 108 96.82

21 Dec-99 114 127.97 60 Mar-03 100 93.84

22 Jan-00 122 107.97 61 Apr-03 107 104.28

23 Feb-00 122 121.97 62 May-03 113 106.69

24 Mar-00 114 108.97 63 Jun-03 135 111.33

25 Apr-00 118 114.97 64 Jul-03 142 135.5

26 May-00 127 118.83 65 Aug-03 133 142.83

27 Jun-00 125 124.62 66 Sep-03 131 129.79

28 Jul-00 126 120 67 Oct-03 128 120.94

29 Aug-00 140 124.4 68 Nov-03 131 140.41

30 Sep-00 139 144.1 69 Dec-03 123 132.77

31 Oct-00 127 126.91 70 Jan-04 125 124.4

32 Nov-00 160 137.87 71 Feb-04 135 124.91

33 Dec-00 152 164.67 72 Mar-04 132 122.36 34 Jan-01 140 153.23 73 Apr-04 134 137.04

35 Feb-01 141 139.95 74 May-04 120 135.42

36 Mar-01 113 130.55 75 Jun-04 111 124.19

37 Apr-01 126 115.51 76 Jul-04 104 113

38 May-01 132 129.88 77 Aug-04 112 102.45

39 Jun-01 136 129.85 78 Sep-04 99 109.05

Table 4.9 : Contd…

Sl. No.

Months Actual value

Forecasted value

Sl. No.

Months Actual value

Forecasted value

79 Oct-04 103 90.52 118 Jan-08 122 123.99

80 Nov-04 100 113.28 119 Feb-08 124 127.47

81 Dec-04 121 99.47 120 Mar-08 106 109.91

82 Jan-05 123 122.17 121 Apr-08 . 106.28

83 Feb-05 132 125.23 122 May-08 . 101.13

84 Mar-05 128 121.63 123 Jun-08 . 103.5

85 Apr-05 124 132.23 124 Jul-08 . 96.02

86 May-05 125 121.7 125 Aug-08 . 100.42

87 Jun-05 121 125.78 126 Sep-08 . 94.36

88 Jul-05 112 120.78 127 Oct-08 . 87.07

89 Aug-05 123 112.77 128 Nov-08 . 95.24

90 Sep-05 111 117.65 129 Dec-08 . 109.49 91 Oct-05 109 105.32 130 Jan-09 . 110.14

92 Nov-05 128 116.25 131 Feb-09 . 114.79

93 Dec-05 164 132.6 132 Mar-09 . 99.64

94 Jan-06 175 165.32 133 Apr-09 . 99.95

95 Feb-06 186 178.66 134 May-09 . 94.77

96 Mar-06 140 176.96 135 Jun-09 . 97.03

97 Apr-06 137 142.3 136 Jul-09 . 89.7

98 May-06 119 135.6 137 Aug-09 . 94.08

99 Jun-06 125 118.82 138 Sep-09 . 88.05

100 Jul-06 111 122.87 139 Oct-09 . 80.8

101 Aug-06 124 113.93 140 Nov-09 . 88.79

102 Sep-06 126 117.23 141 Dec-09 . 103.01

103 Oct-06 117 120.96 142 Jan-10 . 103.66

104 Nov-06 107 127.05 143 Feb-10 . 108.32

105 Dec-06 135 118.4 144 Mar-10 . 93.19

106 Jan-07 128 138.46 145 Apr-10 . 93.46

107 Feb-07 135 133.2 146 May-10 . 88.25

108 Mar-07 131 117.48 147 Jun-10 . 90.47

109 Apr-07 128 132.17 148 Jul-10 . 83.1

110 May-07 122 122.86 149 Aug-10 . 87.46

111 Jun-07 129 123.22 150 Sep-10 . 81.39

112 Jul-07 111 124.32 151 Oct-10 . 74.11

113 Aug-07 114 116 152 Nov-10 . 82.06

114 Sep-07 104 109.23 153 Dec-10 . 96.25

115 Oct-07 92 98 154 Jan-11 . 96.86

116 Nov-07 109 97.43 155 Feb-11 . 101.49

117 Dec-07 123 123.64 156 Mar-11 . 86.32

Table 4.10: Selected measures of predictive performance of Box-Jenkins model

MSE MAPE

Ramnagar

Arrivals 452.67 171.47

Prices 50.54 11.92

Siddlaghatta

Arrivals 622.56 180.75

Prices 52.88 14.04

Fig.4.9. Ex-ante and ex-post forecast of cocoon arrivals in Ramnagar market

Fig.4.10. Ex-ante and ex-post forecast of cocoon prices in Ramnagar market

4.4.1.4 Forecasting the arrivals and prices of cocoon in Ramnagar market

The method of forecasting has been explained in detail in chapter 3. Both Ex-ante and Ex-post forecast are done and it is compared with actual values of observations. The forecast is done up to March 2011. The results of Ex-ante and Ex-post forecast of arrivals and prices of cocoon in Ramnagar market is shown in Tables 4.8 and 4.9. The forecasts are also depicted in the Fig. 4.9 and Fig 4.10. The accuracy of forecasts for both Ex-ante and Ex-post are tested using MSE and MAPE tests. The values MSE and MAPE are presented in Table 4.10, which are found to be least. Forecasted values of arrivals showed an increasing trend and prices showed decreasing trend in Ramnagar market.

4.4.2 Arrivals and Prices of cocoon in Siddlaghatta market

The detailed analysis of forecasting of arrivals and prices of cocoon in Siddlaghatta market has been presented as under.

4.4.2.1 Identification of the model

The tentative models are first identified based on the Auto Correlation Function (ACF) and Partial Auto Correlation Function (PACF) for the different series Yt for selected markets. The computed value of ACF and PACF of Siddlaghatta market is shown in Table 4.11 up to 30 lags. An examination of the ACF and PACF revealed seasonality. However, the series is found to be stationary, since the coefficient dropped to zero after the first or second lag. Each individual coefficient of ACF and PACF are tested for their significance using ‘t’ test. Further, the absence of peak at first values clearly indicate suitability of the choice of non-seasonal difference d=1, to accomplish stationarity series. Hence, based on ACF and PACF many models are tried, finally model (2,1,1) (1,1,1) is tentatively identified for arrivals and (0,1,0) (1,1,1) models for prices in Siddlaghatta market.

4.4.2.2 Estimation of parameters

After identifying the models tentatively the next step is to obtain the estimates by the

method of Least Squares Estimates of the parameters φ and θ for both the markets. Such that the error sum of square is to be minimum.

i.e. S(φ . θ) = et² (φ . θ)

The parameters of the tentatively identified models are estimated by an iterative process and then the residual of each of the models is to be estimated.

4.4.2.3 Diagnostic checking

Residual analysis is carried out to check the adequacy of the models. The residuals of ACF and PACF are obtained from the tentatively identified model. The adequacy of the model is judged based on the values of Box-Pierce Q statistics and AIC. The values of the statistics are shown in Table 4.7. The model (2,1,1) (1,1,1) is found to be the best model for arrivals in Siddlaghatta market and the model (0,1,0) (1,1,1) is found to be the best model for prices, since it had the least statistic for AIC and Q statistics.

4.4.2.4 Forecasting the arrivals and prices of cocoon in Siddlaghatta market

The method of forecasting has been explained in detail in chapter 3. Both Ex-ante and Ex-post forecast are done and it is compared with actual values of observations. The forecast is done up to March 2011. The results of Ex-ante and Ex-post forecast of arrivals and prices of cocoon in Siddlaghatta market is shown in Tables 4.12 to 4.13. The forecasts are also depicted in the Fig. 4.11 and 4.12. The accuracy of forecasts for both Ex-ante and Ex-post are tested using MSE and MAPE tests. The values MSE and MAPE are presented in Table 4.10, which are found to be least. Forecasted values of arrivals showed an increasing trend and prices showed decreasing trend in Siddlaghatta market.

Table 4.11: ACF and PACF of monthly arrivals and prices of cocoon in Siddlaghatta market

Arrivals Prices

Lags ACF PACF ACF PACF

1 -0.02 -0.02 -0.164 -0.164

2 0.00 0.00 -0.031 -0.059

3 0.10 0.10 -0.084 -0.102

4 -0.03 -0.04 0.107 0.076

5 0.01 0.01 -0.149 -0.133

6 -0.11 -0.10 -0.007 -0.054

7 0.03 0.03 -0.040 -0.055

8 0.07 0.07 -0.042 -0.099

9 0.03 0.01 0.033 0.022

10 0.10 0.11 0.116 0.101

11 0.01 0.02 -0.188 -0.178

12 0.01 0.02 0.049 0.006

13 -0.10 -0.08 0.032 0.011

14 -0.04 -0.06 0.036 -0.002

15 0.12 0.12 -0.007 0.069

16 -0.02 -0.06 -0.024 -0.063

17 -0.09 -0.08 -0.082 -0.101

18 0.03 0.07 -0.018 -0.042

19 0.04 0.04 0.025 -0.034

20 -0.01 0.00 -0.021 -0.016

21 0.00 -0.02 -0.053 -0.029

22 0.08 0.09 0.136 0.066

23 -0.02 -0.01 0.002 0.011

24 0.04 0.01 -0.004 -0.009

25 -0.01 0.01 -0.169 -0.184

26 0.08 0.07 0.088 0.030

27 -0.02 -0.01 0.011 0.037

28 0.11 0.07 0.055 0.028

29 0.02 0.04 -0.005 0.051

30 0.00 0.03 0.048 0.035

Table 4.12: Actual and Forecasted values for arrivals of cocoon in Siddlaghatta market

Sl. No.

Months Actual value

Forecast value

Sl. No.

Months Actual value

Forecast value

1 Apr-98 517.13 . 40 Jul-01 715.43 917.38

2 May-98 633.75 . 41 Aug-01 921.33 898.88

3 Jun-98 635.54 . 42 Sep-01 950.14 793.26

4 Jul-98 893.47 . 43 Oct-01 761.76 1073.13

5 Aug-98 954.24 . 44 Nov-01 941.84 925.65

6 Sep-98 668.51 . 45 Dec-01 544.28 842.07

7 Oct-98 981.72 . 46 Jan-02 1036.63 799.83

8 Nov-98 827.15 . 47 Feb-02 1093.06 908.28

9 Dec-98 925.12 . 48 Mar-02 1273.86 1369.38

10 Jan-99 754.19 . 49 Apr-02 1010.07 751.13

11 Feb-99 787.8 . 50 May-02 922.16 1035.08

12 Mar-99 1319 . 51 Jun-02 702.89 815.76

13 Apr-99 934.57 . 52 Jul-02 1024.92 835.87

14 May-99 955.46 1051.62 53 Aug-02 713.94 1028.65

15 Jun-99 761.14 996.4 54 Sep-02 1021.38 817.86

16 Jul-99 889.9 1134.97 55 Oct-02 1006.69 985.97

17 Aug-99 960.24 1091.43 56 Nov-02 1127.18 1050.05

18 Sep-99 784.29 773.05 57 Dec-02 1064.91 870.38

19 Oct-99 1028.51 1120.39 58 Jan-03 653.86 1127.14

20 Nov-99 1237.25 943.77 59 Feb-03 880.99 934.07

21 Dec-99 928.07 1176.11 60 Mar-03 1035.94 1246.25

22 Jan-00 1004 890.77 61 Apr-03 541.57 729.77

23 Feb-00 1038.51 957.7 62 May-03 560.04 790.86

24 Mar-00 1508.8 1514.82 63 Jun-03 433.97 566.32

25 Apr-00 689.6 1052.35 64 Jul-03 796.73 711.73

26 May-00 984.11 929.78 65 Aug-03 917.54 769.52

27 Jun-00 784.21 870.02 66 Sep-03 980.94 873.32

28 Jul-00 822.13 1043.66 67 Oct-03 841.23 968.5

29 Aug-00 877.29 1027.32 68 Nov-03 936.37 967.99

30 Sep-00 900.02 762.87 69 Dec-03 939.25 800.49

31 Oct-00 981.88 1126.71 70 Jan-04 963.11 867.75

32 Nov-00 884.65 1118.47 71 Feb-04 790.64 972.54

33 Dec-00 793.86 914.51 72 Mar-04 968 1161.13

34 Jan-01 1003.15 853.25 73 Apr-04 602.85 604.72

35 Feb-01 930.82 973.2 74 May-04 892.19 716.24

36 Mar-01 1132.9 1455.21 75 Jun-04 1063.32 645.1

37 Apr-01 702.79 680.89 76 Jul-04 1050.51 1008.37

38 May-01 967.24 871.25 77 Aug-04 960.13 1014.63

39 Jun-01 759.72 797.88 78 Sep-04 1022.99 981.08

Table 4.12: Contd…

Sl. No. Months

Actual value

Forecast value

Sl. No. Months

Actual value

Forecast value

79 Oct-04 904.16 990.15 118 Jan-08 1084.91 1219.07

80 Nov-04 1129.96 1021.37 119 Feb-08 1186.86 1084.85

81 Dec-04 887.56 950.79 120 Mar-08 1301.01 1445.9

82 Jan-05 988.02 947.36 121 Apr-08 . 1060.08

83 Feb-05 782.66 962.32 122 May-08 . 1161.54

84 Mar-05 1090.27 1146.02 123 Jun-08 . 1151.42

85 Apr-05 835.18 685.76 124 Jul-08 . 1399.36

86 May-05 985.52 905.52 125 Aug-08 . 1274.65

87 Jun-05 952.13 862.84 126 Sep-08 . 1307.85

88 Jul-05 1091.55 1027.8 127 Oct-08 . 1372.77

89 Aug-05 1078.2 1033.26 128 Nov-08 . 1314.26

90 Sep-05 1083.39 1071.89 129 Dec-08 . 1282.95

91 Oct-05 1098.86 1042.19 130 Jan-09 . 1262.79

92 Nov-05 729.93 1167.12 131 Feb-09 . 1215.94

93 Dec-05 925.74 841.24 132 Mar-09 . 1474.06

94 Jan-06 1021.31 943.15 133 Apr-09 . 1159.74

95 Feb-06 858.81 955.05 134 May-09 . 1253.94

96 Mar-06 1406.48 1187.67 135 Jun-09 . 1230.03

97 Apr-06 1284.39 876.1 136 Jul-09 . 1475.05

98 May-06 1147.87 1166.11 137 Aug-09 . 1350.83

99 Jun-06 1060.41 1043.75 138 Sep-09 . 1385.69

100 Jul-06 1635.69 1159.38 139 Oct-09 . 1447.21

101 Aug-06 1169.81 1323.06 140 Nov-09 . 1393.43

102 Sep-06 1311.63 1248.63 141 Dec-09 . 1361.21

103 Oct-06 1461.18 1230.93 142 Jan-10 . 1343.59

104 Nov-06 1415.83 1295.82 143 Feb-10 . 1292.61

105 Dec-06 1446.32 1257.13 144 Mar-10 . 1555.51

106 Jan-07 1267.42 1353.54 145 Apr-10 . 1239.37

107 Feb-07 1063.17 1215.8 146 May-10 . 1333.76

108 Mar-07 1274.4 1478.87 147 Jun-10 . 1309.85

109 Apr-07 939.99 1075.38 148 Jul-10 . 1555.2

110 May-07 1070.45 1119.61 149 Aug-10 . 1431.41

111 Jun-07 1199.14 1057.23 150 Sep-10 . 1466.74

112 Jul-07 1438.51 1392.57 151 Oct-10 . 1528.57

113 Aug-07 1242.85 1293.93 152 Nov-10 . 1475.36

114 Sep-07 1203.08 1323.93 153 Dec-10 . 1443.53

115 Oct-07 1377.16 1307.88 154 Jan-11 . 1426.41

116 Nov-07 1168.65 1334.44 155 Feb-11 . 1375.72

117 Dec-07 1177.23 1234.19 156 Mar-11 . 1639.18

Table 4.13: Actual and Forecasted values for prices of cocoon in Siddlaghatta market

Sl. No Months Actual value

Forecast value Sl. No. Months

Actual value

Forecast value

1 Apr-98 151 . 40 Jul-01 149 144.39

2 May-98 175 . 41 Aug-01 142 141.15

3 Jun-98 162 . 42 Sep-01 127 141.05

4 Jul-98 171 . 43 Oct-01 109 127.78

5 Aug-98 168 . 44 Nov-01 126 105.06

6 Sep-98 161 . 45 Dec-01 136 127.25

7 Oct-98 161 . 46 Jan-02 125 152.01

8 Nov-98 172 . 47 Feb-02 115 118.18

9 Dec-98 165 . 48 Mar-02 110 110.47

10 Jan-99 174 . 49 Apr-02 111 103.51

11 Feb-99 168 . 50 May-02 92 116.35

12 Mar-99 161 . 51 Jun-02 98 93.11

13 Apr-99 121 . 52 Jul-02 101 99.48

14 May-99 116 144.96 53 Aug-02 103 89.29

15 Jun-99 122 102.96 54 Sep-02 98 99.49

16 Jul-99 120 130.96 55 Oct-02 92 96.85

17 Aug-99 116 116.96 56 Nov-02 90 95.91

18 Sep-99 119 108.96 57 Dec-02 80 86.52

19 Oct-99 118 118.96 58 Jan-03 104 90.88

20 Nov-99 98 128.96 59 Feb-03 111 97.07

21 Dec-99 115 90.96 60 Mar-03 102 111.8

22 Jan-00 136 123.96 61 Apr-03 118 100

23 Feb-00 128 129.96 62 May-03 126 119.22

24 Mar-00 116 120.96 63 Jun-03 153 128.38

25 Apr-00 125 75.96 64 Jul-03 151 155.94

26 May-00 130 137.27 65 Aug-03 139 142.79

27 Jun-00 133 124.57 66 Sep-03 144 131.97

28 Jul-00 132 137.51 67 Oct-03 132 137.29

29 Aug-00 110 128.53 68 Nov-03 138 138.55

30 Sep-00 109 106.95 69 Dec-03 126 137.17

31 Oct-00 115 108.53 70 Jan-04 127 132.84

32 Nov-00 126 113.47 71 Feb-04 135 121.43

33 Dec-00 105 128.58 72 Mar-04 134 132.52

34 Jan-01 120 118.76 73 Apr-04 143 135.72

35 Feb-01 115 113.13 74 May-04 131 139.58

36 Mar-01 130 105.92 75 Jun-04 119 138.24

37 Apr-01 135 109.63 76 Jul-04 110 121.12

38 May-01 140 140.74 77 Aug-04 122 103.99

39 Jun-01 143 139.61 78 Sep-04 105 117.39

Table 4.13: Contd..

Sl.no Months Actual value

Forecast value Sl.no Months

Actual value

Forecast value

79 Oct-04 111 97.59 118 Jan-08 133 126.85

80 Nov-04 98 115.01 119 Feb-08 130 144.29

81 Dec-04 123 92.78 120 Mar-08 106 117.61

82 Jan-05 121 133.66 121 Apr-08 . 105.8

83 Feb-05 135 121.04 122 May-08 . 100.13

84 Mar-05 133 130.87 123 Jun-08 . 101.66

85 Apr-05 137 139.82 124 Jul-08 . 90.17

86 May-05 137 135.37 125 Aug-08 . 96.23

87 Jun-05 131 146.69 126 Sep-08 . 93.84

88 Jul-05 127 130.16 127 Oct-08 . 82.86

89 Aug-05 132 122.09 128 Nov-08 . 79.73

90 Sep-05 122 128.08 129 Dec-08 . 97.31

91 Oct-05 116 115.36 130 Jan-09 . 101.03

92 Nov-05 129 117.84 131 Feb-09 . 110.23

93 Dec-05 157 126.58 132 Mar-09 . 99.43

94 Jan-06 171 162.91 133 Apr-09 . 99.23

95 Feb-06 187 175.41 134 May-09 . 94.81

96 Mar-06 157 184.03 135 Jun-09 . 93.9

97 Apr-06 149 163.93 136 Jul-09 . 82.21

98 May-06 138 144.67 137 Aug-09 . 86.8

99 Jun-06 147 139.1 138 Sep-09 . 85.3

100 Jul-06 126 143.33 139 Oct-09 . 73.14

101 Aug-06 139 127.32 140 Nov-09 . 71.95

102 Sep-06 144 130.41 141 Dec-09 . 86.8

103 Oct-06 126 140.94 142 Jan-10 . 92.78

104 Nov-06 111 125.38 143 Feb-10 . 98.5

105 Dec-06 135 120.97 144 Mar-10 . 83.95

106 Jan-07 130 139.91 145 Apr-10 . 83.7

107 Feb-07 142 138.86 146 May-10 . 78.87

108 Mar-07 142 135.01 147 Jun-10 . 78.59

109 Apr-07 142 145.71 148 Jul-10 . 66.9

110 May-07 141 137.78 149 Aug-10 . 71.85

111 Jun-07 134 141.3 150 Sep-10 . 70.04

112 Jul-07 122 127.46 151 Oct-10 . 58.16

113 Aug-07 123 126.13 152 Nov-10 . 56.37

114 Sep-07 124 116.09 153 Dec-10 . 71.93

115 Oct-07 109 117.72 154 Jan-11 . 77.22

116 Nov-07 113 109.88 155 Feb-11 . 83.86

117 Dec-07 121 130.16 156 Mar-11 . 70.31

Fig4.11. Ex-ante and ex-post forecast of cocoon arrivals in Siddlaghatta market

Fig.4.12. Ex-ante and ex-post forecast of cocoon prices in Siddlaghatta market

5. DISCUSSION

Ramnagar and Siddlaghatta markets are selected to study the fluctuation in cocoon prices. The secondary data on monthly arrivals and prices of cocoons were collected for the study period from 1998 to 2008 from the respective markets. The data was subjected to different statistical tools and the results presented in the previous chapter are discussed and presented under the following heads.

5.1 Growth rates in arrivals and prices of cocoon

5.2 Behaviour of arrivals and prices of cocoon

5.3 Market integration

5.4 Forecasting of arrivals and prices

5.1 Growth rates in arrivals and prices of cocoon in Ramnagar and Siddlaghatta market

The results of growth rates were presented in Table 4.1. The growth rates of arrivals of both Ramnagar and Siddlaghatta markets are found to be significant. But the prices of both Ramnagar and Siddlaghatta markets are found to be negative and non-significant.

Though the compound growth rates are significant in arrivals, it is found to be low, as cocoon production area and supply is restricted for both markets. For Ramnagar market, the farmers are bringing cocoons from Ramnagar, Mandya, Chitradurga and Tumkur. For Siddlaghatta market, the cocoon supply is from kolar, Bangalore rural and Chikballapur. Since each district of Karnataka has almost one cocoon market, so farmers prefer to go nearby market unless proper transport facilities are available.

With reference to growth rates in price, negative growth rates are observed as the prices are reduced over the ten years. In Ramnagar market, the maximum and minimum price observed during the year 1998 was Rs 142 /kg and 110 Rs/kg but in the year 2008, the maximum and minimum price was Rs 129/kg and Rs 92/kg. Similarly in Siddlaghatta market, during the year 1998, the maximum and minimum price was Rs 175/kg and Rs 161/kg but in the year 2008, the maximum and minimum price was Rs 142 and Rs 106/kg.

Cocoon can’t be stored for long time since moth will emerge from cocoon, then it will become useless and silk can’t be reeled. So, farmers have to sell cocoon even if it fetches low price on that day. Import of Chinese silk also leads to decrease the production of Indian silk which in turn reduce the Indian cocoon price. Because of these reasons, the negative growth rate was observed in cocoon (Kshama et al., 2008).

Negative compound growth rate indicates the demand for efficient pricing technique which may make it competitive and increase the growth rates.

Similar methodology is used by Nisha (2004) to study the growth rate of groundnut in India from 1980-1988 and 1991-1994. The results revealed that, in the pre-liberalization period (1980-1988), there is a negative growth rate both in quantity and value.

5.2 Behaviour of Arrivals and Prices of cocoon

5.2.1 Seasonal indices of arrivals and prices of cocoon in Ramnagar and Siddlaghatta markets

To analyze the arrival pattern of cocoon during different months of the year and their impact on price, seasonal indices are computed adopting 12 months centered moving averages. The seasonal variation in arrivals and prices of cocoon in the study markets are presented as follows.

The seasonal indices of monthly arrivals and prices of cocoon in both Ramnagar and Siddlaghatta markets are presented in Table 4.2 and Fig 4.1 and 4.2.

Silk worm feeds on mulberry leaves, which is a perennial plant. From mulberry around five to six harvests can be obtained in a year. The life cycle of silk worm would be

around 25-30 days depending upon climatic conditions like room temperature, humidity etc. then it stops feeding and starts spinning the cocoon. That cocoon is used for reeling silk.

Silk worm reared in hotter months produce less cocoon due to their susceptibility to diseases. Cocoon production will be more, when it has favourable conditions like low temperature accompanied by high humidity (Siddiqui et al., 2001).

Since both Ramnagar and Siddlaghatta cocoon markets are in irrigated region, the cocoon production will be more after the rainy season. Hence the peak season of arrivals of both Ramnagar and Siddlaghatta markets coincide with the ideal months having favourable condition for cocoon production (March).

With regard to their price indices, it is higher during February in Ramnagar market; the reason might be the high quality of cocoon. In Siddlaghatta market, the highest price is in April month which has lowest arrivals. The price of cocoon is fixed by the reelers based on cocoon color, weight, luster and quality and quantity.

Similar seasonal indices are obtained by Prabhakara (1988) while studying the behaviour of major cocoon markets in Karnataka viz. Ramnagar and Vijayapura.

5.2.2 Secular trend in arrivals and prices of cocoon in Ramnagar and Siddlaghatta markets

Trend is long term movement in time series value of a variable over a fairly long period of time. This method is more suitable for the present study because of absence of a prior knowledge regarding the exact mathematical form of the trend function.

The change in trend occurs as a result of general tendency of the data to increase or decrease as a result of some identifiable influences. The Trend component in arrivals and prices of cocoon are presented in Fig. 4.3 to 4.6.

The arrivals of cocoon in both markets are very slowly and gradually increasing, but the quantum of increase in arrivals varied from market to market.

During the year 1998, Ramnagar market recorded high quantity of arrivals and also in price but after that the trend has changed. The Siddlaghatta market registered high quantity of arrivals and also in price during the remaining years of study period.

The trend shows decrease in arrivals during the year 2002 -2004 in both Ramnagar and Siddlaghatta markets. The reason is the occurrence of severe drought due to the failure of rainfall in Southern peninsula. During this period, the cocoon fetched higher price, so positive trend is observed.

In both Ramnagar and Siddlaghatta markets, the price is fixed mainly based on quality apart from quantity of arrival of cocoon. Though the arrivals increased the prices did not show the corresponding decline, this might be due to the fact that the cocoon may be in continuous demand in the locality.

A critical analysis of trend shows slowly increasing trend in arrivals in both the study markets but price of cocoon shows trend equation with mild ups and downs in both the markets.

5.2.3 Cyclical trend in arrivals and prices of cocoon in Ramnagar and Siddlaghatta markets

Cyclical trend in arrivals and prices of cocoon in Ramnagar and Siddlaghatta markets are presented in Fig. 4.7 to Fig 4.8. It could be observed that there exist no cycles in arrivals and prices of cocoon in Ramnagar and Siddlaghatta markets. This is mainly because cycle can be observed only for time series data of 30-50 years and above. As the data is available for 10 years, cycles are not observed in Ramnagar and Siddlaghatta markets.

Similar results are observed by Punitha (2007). It could be observed that there exist no cycles in arrivals and prices of maize and groundnut in Davengere and Hubli markets. As the data is available for 14 years (maize) and 20 years (groundnut), cycles are not observed in any selected markets.

5.3 Market integration

5.3.1 Correlation between arrivals and prices of cocoon in Ramnagar and Siddlaghatta markets

The correlation coefficient is computed to ascertain the pattern of association between market arrivals and prices of cocoon in Ramnagar and Siddlaghatta markets. The results of the analysis are presented in Table 4.3 and Table 4.4.

It could be observed from the Table 4.3, the year wise correlation of both Ramnagar and Siddlaghatta markets showed negative correlation (i.e.) when the quantity of arrivals increases, the price of cocoon decreases.

As far as Table 4.4 considered Ramnagar market shows negative and non-significant relationship between the arrivals and prices of cocoon. It shows apart from arrivals of cocoon, quality also contributing to price. Siddlaghatta market shows negative and significant relationship between the arrivals and prices of cocoon. The arrivals and prices are exactly moving in opposite direction, as arrival increases¸ price decreases and vice versa.

Similar technique is employed by Nagaraj et al. (1987) to study spatial integration of silk cocoon markets in Karnataka. Results revealed that the silk cocoon markets in Karnataka are spatially integrated and there by price efficient.

5.3.2 Concurrent deviation between Ramnagar and Siddlaghatta markets

The concurrent deviation between Ramnagar and Siddlaghatta markets are presented in the Table 4.5.

The arrivals of cocoon in Ramnagar and Siddlaghatta markets show the positive correlation, it indicates the arrivals of Ramnagar market increase with the increase in arrivals of Siddlaghatta market.

Similarly the price of cocoon between two markets shows positive correlation like arrivals. The main disadvantage of the concurrent deviation method is that the significant can’t be tested, only correlation coefficients can be obtained.

5.4 Box-Jenkins Model

As explained earlier (Chapter III), fitting Box-Jenkins models, the other name of ARIMA models, involves a four stage procedure. The discussion is presented in the same order.

5.4.1 Identification of the model

Identification of the model is the first step which involves a greater deal of skill. It is done based on conjunction of the sample Auto Correlation Function with the Partial Auto Correlation Function (PACF). ACF and PACF for both markets are presented in Table 4.6 and 4.11. Since the method of identification does not lay down any hard and fast principles, several possible models are tentatively identified and the following yielded the best results.

5.4.2 Estimation

Having tentatively identified the model, next the parameters which minimize the sum of squares of errors are estimated. The estimated models for arrivals and prices of cocoon are presented below.

1. Monthly arrivals of cocoon in Ramnagar market : (1,1,3) (1,1,1)

2. Monthly prices of cocoon in Ramnagar market : (0,10) (1,1,1)

3. Monthly arrivals of cocoon in Siddlaghatta market : (2,1,1) (1,1,1)

4. Monthly prices of cocoon in Siddlaghatta market: ((0,1,0) (1,1,1)

5.4.3 Diagnostic checking

The residuals of estimated models are examined for testing the randomness of series and analyzed to determine the adequacy of the estimated models.

For all the series of cocoon arrivals and prices, Box-Pierce Q statistic yielded non- significant and AIC is minimum. Seasonality is found and forecast consideration is the best. So these models are chosen.

5.4.4 Forecasting

Ex-ante and Ex-post obtained by the Box-Jenkins methods are presented in Table 4.8, 4.9 and Table 4.12, 4.13. The forecasts from the various models are checked for their efficacy by comparing them with the actual values

The similar model (Box-Jenkins) is used by Achoth (1985) analyzed the supply, price and trade of Indian tea by fitting ARIMA model to data on prices and production. The forecasts yielded reasonably good results as judged from the tests of their efficiency. The forecasts of prices are superior when compared to the forecasts of quantities, which is attributed to the highly structured pattern of price behaviour.

6. SUMMARY AND POLICY IMPLICATIONS

Sericulture is rearing of silk worms, is well known as a highly employment oriented, low capital intensive activity ideally suited to the conditions of a labour-abundant and agro-based industry. Silk is the queen of textiles, have endearing qualities such as natural sheen, light weight with high durability. India has the unique distinction of producing all the four types of silk viz., mulberry, tasar, muga and eri. Among them, mulberry silk is predominant and accounts for 88 per cent of the total natural silk produced in India, which is taken for present study.

Compound growth rates were calculated to find the growth in arrivals and prices of cocoon over the ten years.

A multiplicative model of time series was used on arrivals and prices data for each of these markets. A 12 month centered moving average was calculated for the purpose of estimating final stabilized seasonal indices. The trend cycle components were obtained by dividing the original observation by seasonal index of corresponding months. These deseasonalized data contain trend, cyclical and irregular components. This trend cycle components are plotted against time for examining cyclical behaviour. If there is any existence of cycle, periodicity of cycle is noted. Again moving average of length equal to periodicity of cycle is computed for eliminating cyclical behaviour. The order of polynomial regression was determined based on the highest R² values.

In order to know the market integration, the correlation coefficients were calculated for all the prices and arrivals of market. Concurrent deviation was used to know the arrivals and prices in both the markets were moving in the same direction or not.

The Box-Jenkins is fitted to arrivals and prices of both Ramnagar and Siddlaghatta market. If there is seasonality in the data, then seasonal ARIMA model is used. Before going to application of Box-Jenkins analysis, the data should be stationary series. If the series is not stationary, it could be removed by differencing. The differenced series does not distort the features of the series.

Making use of differenced series (which is stationary), the ACF and PACF were computed because, it helps in tentatively identify the models. Then the parameters of all tentatively identified models were estimated by iterative process. These estimated models were subjected to diagnostic checking in order to determine the adequacy of the models. The residues of estimated models were examined for testing the randomly of series and for its significance. The ACF and PACF of residuals were tested using Box-Jenkins Q statistic. Both Ex-ante and Ex-post forecast was done for all the best models.

Therefore the present study is an attempt to study the fluctuation in silk cocoon prices in selected markets. Hence, the present study is conducted with the following objectives.

1) To study the growth in arrivals and prices of cocoon in the selected markets.

2) To study the price behaviour of cocoon.

3) To analyze the market integration.

4) To forecast the price of cocoon.

Ramnagar and Siddlaghatta cocoon market have been selected for the study as they are the important reeling cocoon markets in Karnataka. The study was exclusively based on secondary data. The information on monthly data of cocoon arrivals and prices was collected for the study period from 1998-99 to 2007-08 from the respective markets.

Major findings of the study

Growth in arrivals and prices of cocoon

• In Ramnagar market, the arrivals in cocoon have recorded a significant compound growth rate of 0.0584, but the value of cocoon recorded a negative compound growth rate of -0.0070.

• In Siddlaghatta market, the cocoon arrivals reported a significant compound growth rate of 0.1407, but the value of cocoon recorded a negative compound growth rate of -0.0178.

Seasonal indices

• Seasonal indices of arrivals and prices of cocoon in Ramnagar revealed that the highest arrival index was noticed in the month of March (139.00) and the lowest arrival was noticed in the month of August (84.63). The highest price index was noticed in the month of February (109.53).

• Seasonal indices of arrivals and prices of cocoon in Siddlaghatta recorded that the highest arrival index was noticed in the month of March (125.74) and the lowest arrival was noticed in the month of April (84.97). The highest price index was noticed in the month of April (110.23).

Secular trend

• The pattern of trend in arrivals and prices of cocoon were almost similar in study markets.

• For both the markets, the 6th order polynomial regression equation shows increasing

trend in arrivals and for prices, though it was fluctuating with ups and downs.

Cyclical trend

• No cyclical trend was observed in both arrivals and prices of cocoon in selected markets. The cyclical trend in selected markets showed that there were no constant period between cycles in both arrivals and prices.

Association between arrivals and prices

• Correlation coefficient was computed to ascertain the pattern of association between market arrivals and prices of cocoon in selected markets.

• Negative relationship between arrivals and prices was noticed for Ramnagar market and then negative and significant relationship was observed for Siddlaghatta market.

• In concurrent deviation method, positive relationship was noticed for arrivals between Ramnagar and Siddlaghatta market. Similarly positive relationship was recorded for prices between Ramnagar and Siddlaghatta market.

Box-Jenkins model

The estimated models for arrivals and prices of cocoon are presented below:

• Monthly arrivals of cocoon in Ramnagar market : (1,1,3) (1,1,1)

• Monthly prices of cocoon in Ramnagar market : (0,10) (1,1,1)

• Monthly arrivals of cocoon in Siddlaghatta market : (2,1,1) (1,1,1)

• Monthly prices of cocoon in Siddlaghatta market: ((0,1,0) (1,1,1)

POLICY IMPLICATIONS

The implications based on the findings of the present study are as follows.

1. Stochastic means being or having a random variable. A model involving a random variable or chance factor is called stochastic model or probability model. A stochastic model is a tool for estimating probability distribution of potential outcome by allowing for random variation in one or more inputs over time. Stochastic model helps to assess the interaction between variables and are useful tools to numerically evaluate quantities.

2. The growth rates of arrivals and prices of cocoon are found to be very low over the ten years. So the cocoon production area can be increased by providing some loans, incentives to farmers. Policy measures should be brought out to have minimum support price for cocoon.

3. Seasonal indices indicate that the arrivals are high in March in both the markets and low in August (Ramnagar), April (Siddlaghatta). The prices are high in February (Ramnagar), April (Siddlaghatta) and low in October (Ramnagar), November (Siddlaghatta). Hence, the farmer needs to plan their cocoon production which comes to harvest in the months where prices are high.

4. All four models are found to be best for arrivals and prices. ARIMA model results reveal that usually the arrivals are high in the month of March in both Ramnagar and Siddlaghatta markets. In case of price, it is noticed in the month of September and December in Ramnagar market and in April in Siddlaghatta market. To avoid market glut, in the above markets, space for displaying cocoons, resting place for farmers etc., need to be provided by the market officials.

REFERENCES

Achoth, L., 1985, Supply price and trend of Indian tea-An econometric analysis. Ph.D. Thesis, Uni.Agric.Sci. Bangalore (India).

Amitkar Attein, R.B. and Pramod Kumar, 2004, Marketing in Himachal Pradesh and integration of Indian apple market. Indian. J. Agric. Marketing (Conf.spl.) 18(3):243-261.

Ashalatha, 2000, Export trade performance of Indian cashew. M.Sc. Thesis, Uni.Agric.Sci. Bangalore (India).

Balapppa Shivaraya, 2002, Infrastructure for price stabilization of potato in Karnataka. Ph.D. Thesis, Uni.Agric.Sci. Dharwad (India).

Beenstock, M. and Bansali, R.J., 1981, Analysis of IOWA price series by auto-regressive model fitting techniques. J. Agric. Econ. 31(2): 237-242.

Bhat Vishwanath, S., 1980, Temporal and Spatial variations in arrivals and prices of paddy and groundnut in selected markets of Karnataka- An economic analysis. M.Sc. (Agri) Thesis, Uni.Agric.Sci. Bangalore (India).

Bisalaiah, S and Patil, S.V., 1987, Technological base and Agricultural transformation of Karnataka, Agric. Situation in India. 42: 367-371.

Chatfield, C and Protharo, D.L., 1973, Box and Jenkins seasonal forecasting problems in a case study. J. Roy. Statist. Soc. A. 136(3): 295-336.

Chatfield, C., 1977 Recent Developments in Time series Analysis. J. Roy. Statist. Soc. A. 140(4):492-510.

Chengappa, P.G., 1980, An analysis of Indian coffee Prices - A Spectral approach. M.Sc.(Agri) Thesis, IARI, New Delhi.

Chengappa, P.G., 1981, Growth rates of area, production and productivity of coffee. Indian. J. Coffee Res. 11(2): 19-26.

Desai, M.N.R., 2001, Export potential of mango in Northern Karnataka- An Economic analysis. Ph.D. Thesis, Uni.Agric.Sci. Dharwad (India).

Devaiah, M.C, Venkatagiriyappa and Achoth Lalith, 1988, Spatial integration and price relationship of Ramnagaram over minor silk cocoon markets of Karnataka. Proceedings of the international congress on tropical sericulture, Central Silk Board, 77-84.

Dudhat .B.L and Khunt.K.A., 2006, Growth and projection of gap between the demand and supply of Quality seeds in Gujarat. Agricultural Marketing. 59 (3):48-55.

Ejiga, N.O. and Robinson,K.L.,1981, The Economics of cowpea marketing in Nigeria, Cornelio International Agricultural Development Monograph, Department of Agricultural Economics, New York, State college of Agriculture Cornelio University. 82 : 73.

Gangadharappa, H., 2005, A Statistical study of variation in arrivals and prices of potato in the selected markets of Karnataka. M.Sc. (Agri) Thesis, Uni. Agric. Sci. Dharwad (India).

George, P.S. and Govindan, A., 1975, Potato cycle In Ahmedabad Market, A Harmonic Analysis. Agricultural Situation in India, 569-573.

Gill, K.S. and Johl, S.S., 1970, Gram price structure in Punjab. Agricultural Situation in India, 25:695-704.

Govardan, 1978, Marketing of chillies in Dharwad district, M.Sc (Agri) Thesis, Uni.Agric.Sci. Bangalore (India).

Govindan, A., 1974, Analysis of Price Behaviour and retail margins in selected food grain markets in India. An application of spectral analysis. Ph.D.Thesis, IARI, New Delhi.

Granger, C.W.J. and Newbold, P., 1970, Spectral methods. Econometrica. 30: 424-438.

Gurumallappa, T.M., 1972, An economic analysis of marketing of groundnut in Raichur district, M.Sc. (Agri.) Thesis, Uni.Agric.Sci. Bangalore (India).

Jayesh, T., 2001, Production and export performance of selected spices of south India- an economic analysis. M.Sc. (Agri) Thesis, Uni.Agric.Sci. Bangalore (India).

Kahlon, A.S and Singh, B., 1968, Marketing of groundnut in Punjab, Tech.Bull. Punjab Agricultural Uni. 1-76.

Kasar, D.V., Raut, R.C and Rasane, V., 1996, Behaviour of prices and arrivals of red chillies – A case study from Maharashtra. Indian. J. Agric. Marketing, 10(3): 78-81.

Kaur, H., Kaur, J and Rangi, P.S., 2002, Growth performance of pulses in India: An interstate analysis, Agricultural Marketing, 66(4): 34-40.

Keith, Virndar, khatana, V.S., Ilangantileke, S.G., Jagpal and Kumar Devendra, 1997, Economics of Potato Storage in Northern India. Working paper, Inter. Potato Centre, 5:1-23.

Kerur.N.M.2007, Policy Reforms and performance of Regulated Markets in Karnataka. Ph.D. Thesis, Uni.Agric.Sci. Dharwad (India).

Krishnaswamy, L., 1975, Behaviour of market arrivals of food grains in Warangal district of Andhra Pradesh. Indian J. Agric. Marketing. 12(1&2):6.

Kshama Giridhar,J.C., Mahanta, Ashok Laxmanrao Deole and B.M.Kantharaju, 2008, Raw silk Production:2007-08, Indian Silk, 47(5): 43-44.

Lanciotti, C., 1990, Forecasts of monthly prices for a group of dairy products – An application of the Box-Jenkins techniques. Rivista-di-Economics-Agraria. 45(3):465-492.

Legesse, D., 2000, Production and marketing of wheat in Northern Karnataka- An Economic analysis. M.Sc. (Agri) Thesis, Uni.Agric.Sci. Dharwad (India).

Leuthold, R.M., Maccomnick, Schmity and D.G.Waltis, 1970, Forecasting daily hog prices and quantities: a study of alternate forecasting technique. J. Ame. Statist. Assoc. 65(1):90-107.

Mahesh, N., 2000, Economics constraints facing the Indian Tea Industry: strategies for post WTO era. Ph.D. Thesis, Uni.Agric.Sci. Bangalore (India).

Makridakis, S and Hibbon,M., 1979, Accuracy of forecasting: An empirical investigation. J. Roy. Statist. Soc. A. 41(2):97-145

Mastny, V., 2001, The use of Box-Jenkins methodology to predict the price development of agricultural commodities. Acta Unierisatatis Agriculturae et Silviculturae- Mendelianae-Brunensis, 49(2):165-172.

Mithlesh kumar, 2006, Temporal changes in dairy industry in India. M.Sc. (Agri) Thesis, Uni. Agric. Sci. Dharwad (India).

Mruthyujaya, Bisaliah, S., and Srinivasan, V.R., 1982, Pace and Pattern of Agricultural output growth in Karnataka, Bulletin published by Project planning and Monitoring Cell, Uni. Agric.Sci. Bangalore (India).

Mundinamani, S.M., 1985, Organizational structure conduct and performance of selected markets of Dharwad district in Karnataka state with special reference to marketing of groundnut. M.Sc. (Agri) Thesis, Uni.Agric.Sci. Bangalore (India).

Mundinamani, S.M., Basavaraja, H., Hosamani, S.B and Srinivasagowda, M.V., 1991, Behaviour market arrivals and prices of groundnut in Karnataka- An Economic analysis. Karnataka. J. Agric. Sci. 4(1-2):36-40.

Nagaraj, N, Achoth Lalith, Bisaliah, S., Ramanna, R. and Chinnaswamy, K.P., 1987, Spatial integration and price leadership in silk cocoon marketing of Karnataka. Sericologia. 22(2): 229-236.

Naik Gopal and Babu, K.R., 1993, Demand and Supply Prospects for High Quality Raw Silk. Oxford and IBH Publishing Co.Pvt.Ltd, New Delhi.

Newbold, P. and Granger, C.W.J., 1974, Experience with forecasting Univariate time series and the combination of forecasts. J. Roy. Statist. Soc. Australia, 137:131-165.

Nisha Varghese, 2004, Export of groundnut from India under liberalization regime- An economic analysis, Ph.D Thesis, Uni. Agric. Sci. Dharwad (India).

Parameshwarappa, K.J., 1997, An economic analysis of domestic prices of Indian silk and export trade of silk goods. M.Sc. (Agri) Thesis, Uni. Agric. Sci. Bangalore (India).

Patel, A.S., Patel, H.F., and Anil Shishodia, 1996, Performance of Agriculture in Gujarat-1, Artha vikas, 32(1): 36-39.

Prabhakara, Y.S., 1988, An economic analysis of silk cocoon marketing in Karnataka. M.Sc. (Agri) Thesis, Uni. Agric. Sci. Bangalore (India).

Protharo, D.L, and K.F.Wallis, 1976, Modelling micro-economic time series. J. Roy. Statistic. Soc. A. 139: 468-500.

Punitha, S.B., 2007, A Comparative analysis of market performance of agricultural commodities – An Economic approach, M.Sc. (Agri) Thesis, Uni. Agric. Sci. Dharwad (India).

Rajashekar, K. R., 2005, Statistical behaviour of price variation of major vegetables in Bangalore and Mysore markets. M.Sc Thesis, Uni. Agric. Sci. Dharwad (India).

Rath, N., 1980, A note on Agricultural Production in India during 1955-78, Indian. J. Agric.Econ. 35 (2): 94-103.

Ravikumar, K.N., Sreelakshmi, K and Raju, V.T., 2001, Trends in arrivals and prices of selected commodities in Anakapalle regulated market. J. Institute. Econ. Res. 23:41-48.

Satya Pal, Ramasubramanian,V and Mehta, S.C., 2007, Statistical models for Forecasting Milk Production in India, J. Ind. Soc. Agril. Statist., 61(2), 2007: 80-83.

Schmity, Andrew and Watts Donald, C., 1970, Forecasting wheat yields: Application of parametric time series modelling. Am. J. Agric. Econ. 52:247-254.

Shenoy, J.R and Ravindran, T.C., 1972, Fluctuations in the wholesale price of arecanut in Indian markets during 1950-1969. Arecanut and Spices, 3:7-11.

Shwetha, B.2003, Production and export competitiveness of selected marine fish products- A case study of Dakshina Kannada district of Karnataka. M.Sc. (Agri) Thesis, Uni. Agric. Sci. Dharwad (India).

Siddiqui. A.A., Chauhan, Tayal, M.K. and Singh, B.D., 2001, Breeding of thermo-tolerant bivoltine silkworm genotype for unfavourable season. Proceedings of National Seminar on Mulberry Sericulture Research, Bangalore, Nov 26-28. p. 568.

Singh, I.J., Rao, K.N. and Karwasra, J.C., 1997, Regional variations in Agricultural Performance in India, Indian. J. Agri. Econ. 52(3): 374-385.

Singhal, A.L., 1986, Rapeseed mustard price structure in Uttar Pradesh, Indian. J. Agri. Econ. 34:2-9.

Thampan, P.K., 1994, Food grain Production in India, Indian Farmers Times, 12 (6): 7-9.

Tripathy, G. and Srinivasa gowda, P., 1993, Agricultural Trend in Orissa in 1970-80, Agricultural situation in India, 48(1): 25-27.

Varuna, 2005, Analysis of export and pricing of black pepper. M.Sc. Thesis, Uni. Agric. Sci. Dharwad (India).

Vinayakumar, 2007, Changes in cereals economy of Karnataka: Pre and Post WTO analysis. M.Sc. (Agri) Thesis, Uni. Agric. Sci. Dharwad (India).

Yin Runsheng and Min, R.S., 1999, Forecasting short-term timber prices with Univariate ARIMA model. J. Ame. Statis. Assoc. 25(1):154-158.

Yogisha, G.M, Karnool, N.N., Vijaya kumar, H.S. and Basavaraja, H., 2007, Trends and seasonal variations in arrivals and prices of potato in kolar district. Agricultural Marketing, 69(4):26-28.

APPENDIX I

State wise Area and Raw Production of Mulberry Silk

Unit: Area: ha, Raw silk: Million tonnes

State Area Raw silk

Traditional states

Andhra Pradesh 42,458 4,485.32

Jammu & Kashmir 4,000 105

Karnataka 97,647 8,240

Tamil nadu 10,043 1,368

West Bengal 14,569 1,660.36

Subtotal (a) 1,68,717 15,858.68

Non-traditional states

Arunachal Pradesh 236 1

Assam 2500 4

Bihar 408 5

Chattisgarh 365 6

Himachal Pradesh 1,685 20

Jharkhand 100 1

Kerala 1,341 14

Madhya Pradesh 1,059 50

Maharashtra 2,647 125

Manipur 5,914 80

Meghalaya 918 2

Mizoram 1,680 6

Nagaland 405 1

Orissa 213 2.5

Punjab 250 0.5

Rajasthan 210 0.3

Sikkim 148 0.2

Tripura 1,407 8

Uttar Pradesh 827 30

Uttarkhand 862 15

Subtotal(b) 23,176 386

Grand total (a+b) 1,91,893 16,245

APPENDIX II Export earnings from silk items

Value: Crore Rs

Item wise Export 2007-08

Natural silk yarn, Fabrics, Made-ups 773.63

Ready made garments 479.38

Silk carpets 32.22

Silk waste 7.31

Total 1,292.54

APPENDIX III Country wise silk export earnings

Value: Crore Rs

Country 2007-08 Country share

(Percent)

USA 299.83 23.2

UK 183.01 14.2

UAE 102.03 7.9

Italy 82.87 6.4

German 64.44 5.0

Spain 67.48 5.2

Hong Kong 22.53 1.7

France 42.78 3.3

Tanzania Rep 3.77 0.3

Saudi Arabia 29.38 2.3

Others 394.42 30.5

Total 1,292.54 100

PRICE BEHAVIOUR OF MULBERRY SILK COCOON IN

RAMNAGAR AND SIDDLAGHATTA MARKET – A

STATISTICAL ANALYSIS APPROACH

R. BHARATHI 2009 Mr. Y. N. HAVALDAR

MAJOR ADVISOR

ABSTRACT Silk is the queen of textiles, have endearing qualities such as natural sheen, light

weight with high durability. The present study was conducted to study the fluctuations in silk cocoon prices in Ramnagar and Siddlaghatta markets. The information on prices and arrivals of cocoon were collected from the respective markets for the study period from 1998-99 to 2007-08.

In case of arrivals, the growth rate was found to be positive and significant in Ramnagar and Siddlaghatta markets. But in case of prices, the growth rate was found to be negative and non-significant in both the markets.

Seasonal indices of arrivals and prices of cocoon in Ramnagar market revealed that the highest arrival index was noticed in the month of March (139.00) and the highest price index was noticed in the month of February (109.53). Similarly in Siddlaghatta market, the highest arrival index was noticed in the month of March (125.74) and the highest price index was noticed in the month of April (110.23). No cyclical index was observed in both arrivals and prices of cocoon in both the markets.

The data was fitted to sixth degree polynomial and the increasing trend was observed for arrivals in both Ramnagar and Siddlaghatta markets.

Negative relationship between arrivals and prices was noticed for Ramnagar market and then negative and significant relationship was observed for Siddlaghatta market. In concurrent deviation method, positive relationship was noticed for arrivals between Ramnagar and Siddlghatta markets. Similarly positive relationship was recorded for prices between Ramnagar and Siddlaghatta markets.

Forecasted values of arrivals showed an increasing trend and prices showed decreasing trend in Ramnagar markets. Similarly forecasted values of arrivals showed an increasing trend and prices showed decreasing trend in Siddlaghatta market.