sampling errors
TRANSCRIPT
Sampling Designs and
Sampling Procedures
Chapter 16
Presented by:
Qadiruddin SufiSameen EjazTooba Farrukh
Under discussion
Sampling terminology Sampling concepts Random vs. non random sampling Types of systematic errors Types of probability & non probability
samples Appropriate sample design
SAMPLING DESIGNS
SAMPLING TERMINOLOGY
SAMPLINGThe process of using a small number of items or
parts of a larger population to make conclusion about the whole population.
SAMPLEA subset or some part of a larger population.
POPULATION(UNIVERSE)A complete group of entities sharing some common
set of characteristics.
POPULATION ELEMENTAn individual member of a specific population.
CENSUSAn investigation of all the individual elements
making up a population.
WHY SAMPLE?
PRAGMATIC REASON
Sampling cuts costs, reduces labor requirements and gather vital information quickly.
ACCURATE AND RELIABLE RESULTS
If properly selected are sufficiently and accurate in most cases. If the elements of a population are quite similar only a small sample is necessary to accurately portray the characteristics of interest.
DESTRUCTION OF TEST UNITS
If there is a finite population and everyone in the population participates in the research and cannot be replaced, no population element remain to be selected as sampling units. The test units have been destroyed.
PRACTICAL SAMPLING CONCEPTS
Researchers must make several decisions before a sample is taken.
Define the target population
Select a sample frame
Determine if a probability or non probability sampling method will be
chosen
Plan procedure for selecting sample units
Determine sample size
Select actual sampling units
Conduct fieldwork
STEP 1 DEFINING THE TARGET POPULATION
TARGET POPULATIONspecific, complete group relevant to the research project.
The question “To whom do we want to talk?”must be answered .It may be users, on users ,recently hired employees ,doctors. To implement the sample in the field, tangible characteristics should be used to define the population.
STEP 2 SELECT A SAMPLE FRAME
SAMPLING FRAME The list of elements from which a sample
may be drawn, also called working population.The sampling frame is also called working
population because it provides the list that can be worked with operationally.
MAILING LISTS A list of the names, addresses and phone numbers
of specific populations.
REVERSE DIRECTORY A directory similar to a telephone directory in
which listings are by city and street address or by telephone numbers rather than alphabetical by last name.
SAMPLING FRAME ERROR Error that occurs when certain sample elements
are not listed or available and are not represent in the sampling frame.
SMAPLING UNITS A single element or group of elements subject to
selection in the sample
PRIMARY SAMPLING UNIT(PSU) A unit selected in the first stage of sampling.
SECONDARY SAMPLING UNIT A unit selected in the second stage of sampling
Sampling Errors
Random Sampling Error
Statistical fluctuation that occurs because of chance variation in the elements selected for a sample is called random sampling error
Sampling error- function of sample size
Sampling error
Population Population
Sampling error
Sample Sample
Systematic / Non sampling Error
Errors resulting primarily from some imperfect aspect of research design or from a mistake in the execution of research
Less than perfectly representative sample
Random sampling error, systematic error combine to give less than perfectly representative sample.
Systematic errori. Sampling frame errorii. Non response error
Non response error Statistical difference between a survey
that included only those who responded and a survey that includes also those who failed to respond
Actual sample is drawn from a population different from the ideal.
Total Population
Planned Sample
Actual Sampl
e
Sampling frame
Sampling frame error
Random sampling error
Non response error
Probability vs. Non Probability Sampling
Probability is not known
Each element chosen on basis of convenience or judgment
Best for research purposes
Every element in population has known probability
Each has non zero probability
Mostly preferred over non probability sampling
Non probability sampling
Convenience sampling
Judgment sampling Experienced individual selects the
sample based upon some appropriate characteristic of the sample members
Quota sampling Ensures that certain characteristics of
a population sample will be represented to the exact extent that the investigator desires.
Sample showing different student categories
punjabsindhbalochistanpeshawar
Snowball sampling Technique used to locate members of
rare population by referrals
Reduced sample sizeReduced cost
Bias may enter
Probability sampling
Probability Sampling
Chance based selection procedure
Probability Sampling techniques:Simple random sampling
Systematic sampling
Stratified samplingProportional versus disproportional sampling
Cluster sampling
Multistage area sampling
Simple Random Sampling
This assures that each element in the population has an equal chance of being included in the sample
Systematic Sampling
A procedure in which an initial starting point is selected by random process and then selects item at a pre-selected interval
Stratified sampling
A sub-sample is drawn utilizing simple random sampling within each stratum; more or less equal on some characteristics
Proportional stratified sampleNumber of sample in each stratum is in proportion to the population size at that stratum
Disproportional stratified sampleSample size for each stratum is allocated according to the analytical considerations
Cluster sampling
The primary sampling unit is not the individual element in the population but a large cluster of elements
Area Sampling where the primary sampling unit is a geographic area
Multistage Sampling
Sampling that involves using a combination of other probability sampling techniques
Sample Design Selection
Degree of Accuracy Resources Time Advanced knowledge National versus Local Project Need for Statistical Analysis
Internet Sampling
Web Site Visitors Panel Sampling Recruited Ad Hoc samples Opt-In Lists
YOUR TURN NOW
AN investigation of all the individual elements making up a population is called
1. Sample2. Census3. Population element4. Sampling unit
The list of elements from which a sample may be drawn called
1. Target population2. Sample size3. Sample frame4. Random Sampling
Which type of non probability sampling technique has more likelihood of having a self selection bias
1. Convenience 2. Judgment3. Quota4. snowball
What are the two types of systematic errors we have covered
1. Sampling frame and sample bias2. Sampling frame and non response
error3. Non response and non sampling error4. Sampling frame and response bias