dr. michael r. hyman, nmsu statistics for a single measure (univariate)
Post on 21-Dec-2015
218 views
TRANSCRIPT
![Page 1: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/1.jpg)
Dr. Michael R. Hyman, NMSU
Statistics for a Single Measure (Univariate)
![Page 2: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/2.jpg)
2
![Page 3: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/3.jpg)
3
Wrong Ways to Think About Statistics
![Page 4: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/4.jpg)
4
Evidence
![Page 5: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/5.jpg)
5
Descriptive Analysis
Transformation of raw data into a form that make them easy to understand and interpret; rearranging, ordering, and manipulating data to generate descriptive information
![Page 6: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/6.jpg)
6
Analysis Begins with Tabulation
![Page 7: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/7.jpg)
7
Tabulation
• Tabulation: Orderly arrangement of data in a table or other summary format
• Frequency table
• Percentages
![Page 8: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/8.jpg)
8
Frequency Table
• Numerical data arranged in a row-and-column format that shows the count and percentages of responses or observations for each category assigned to a variable
• Pre-selected categories
![Page 9: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/9.jpg)
9
Sample Frequency Table
![Page 10: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/10.jpg)
10
Sample SPSS Frequency Output
![Page 11: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/11.jpg)
11
SPSS Histogram Output
![Page 12: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/12.jpg)
12
Base
• Number of respondents or observations (in a row or column) used as a basis for computing percentages
• Possible bases
– All respondents
– Respondents who were asked question
– Respondents who answered question
• Be careful with multi-response questions
![Page 13: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/13.jpg)
13
Measures of Central Tendency
• Mode - the value that occurs most often
• Median - midpoint of the distribution
• Mean - arithmetic average– µ, population– , sampleX
![Page 14: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/14.jpg)
14
Measures of Dispersion or Spread for Single Measure
• Range
• Inter-quartile range
• Mean absolute deviation
• Variance
• Standard deviation
![Page 15: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/15.jpg)
15
150 160 170 180 190 200 210
5
4
3
2
1
Value on Variable
Fre
quen
cy
Low Dispersion
![Page 16: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/16.jpg)
16
150 160 170 180 190 200 210
5
4
3
2
1
Fre
quen
cy
Value on Variable
High Dispersion
![Page 17: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/17.jpg)
17
Range as a Measure of Spread
• Difference between smallest and largest value in a set
• Range = largest value – smallest value
• Inter-quartile range = 75th percentile – 25th percentile
![Page 18: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/18.jpg)
18
Deviation Scores
Differences between each observed value and the mean
xxd ii
![Page 19: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/19.jpg)
19
Average Deviation
0)(
n
XX i
![Page 20: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/20.jpg)
20
Mean Squared Deviation
n
XXi 2)(
![Page 21: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/21.jpg)
21
Variance
2
2
S
Sample
Population
![Page 22: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/22.jpg)
22
Variance
1)2
2
nXX
S
![Page 23: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/23.jpg)
23
Variance
• Variance is given in squared units
• Standard deviation is the square root of variance
1
2
n
XX iS
![Page 24: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/24.jpg)
24
Measure ofCentral Measure of
Type of Scale Tendency Dispersion
Nominal Mode NoneOrdinal Median PercentileInterval or ratio Mean Standard deviation
Summary: Central Tendency and Dispersion
![Page 25: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/25.jpg)
25
Distributions for Single Measures
![Page 26: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/26.jpg)
26
Symmetric Distribution
![Page 27: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/27.jpg)
27
Skewed Distributions
![Page 28: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/28.jpg)
28
Normal Distribution
• Bell shaped• Symmetrical about its mean• Mean identifies highest
point• Almost all values are within
+3 standard deviations• Infinite number of cases--a
continuous distribution
![Page 29: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/29.jpg)
29
2.14%
13.59% 34.13% 34.13% 13.59%
2.14%
Normal Distribution
![Page 30: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/30.jpg)
30
Standard Normal Curve
• The curve is bell-shaped or symmetrical
• About 68% of the observations will fall within 1 standard deviation of the mean
• About 95% of the observations will fall within approximately 2 (1.96) standard deviations of the mean
• Almost all of the observations will fall within 3 standard deviations of the mean
![Page 31: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/31.jpg)
31 85 115100 14570
Normal Curve: IQ Example
![Page 32: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/32.jpg)
32
Standardized Normal Distribution
• Area under curve has a probability density = 1.0
• Mean = 0
• Standard deviation = 1
![Page 33: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/33.jpg)
33
0-1-2 2 z
Standardized Normal Curve
1
![Page 34: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/34.jpg)
34
Standardized Normal is Z Distribution
–z +z
![Page 35: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/35.jpg)
35
xz
Standardized Scores
Used to compare an individual value to the population mean in units of the standard deviation
![Page 36: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/36.jpg)
36
Linear Transformation of Any Normal Variable into a Standardized Normal
Variable
-2 -1 0 1 2
Sometimes thescale is stretched
Sometimes thescale is shrunk
X
xz
![Page 37: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/37.jpg)
37
Data Transformation
• Data conversion
• Changing the original form of the data to a new format
• More appropriate data analysis
• New variables
![Page 38: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/38.jpg)
38
Data Transformation
Summative Score =
VAR1 + VAR2 + VAR 3
![Page 39: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/39.jpg)
39
Index Numbers
• Score or observation recalibrated to indicate how it relates to a base number
• CPI - Consumer Price Index
![Page 40: Dr. Michael R. Hyman, NMSU Statistics for a Single Measure (Univariate)](https://reader034.vdocuments.site/reader034/viewer/2022042821/56649d5f5503460f94a3fa8a/html5/thumbnails/40.jpg)
40
Recap
• Count/frequency data
• Measures of central tendency
• Dispersion from central tendency
• Data distributions
– Symmetric versus skewed
– (Standardized) normal
• Data transformation