HOMEWORK EXERCISE  MEASUREMENT AND CENTRAL TENDENCY
SUMMARIZING DISTRIBUTIONS
1. Calculate all appropriate summary statistics for each distribution
2. Pictorially depict the distribution of arrests
3. Pictorially depict the distribution of gender
HOMEWORK EXERCISE  VARIABILITY
MEASURES OF DISPERSION
Assignment: compute each measure of dispersion
HOMEWORK EXERCISE – CROSSTABULATION
RELATIONSHIP BETWEEN CATEGORICAL VARIABLES
You are a Captain in the Research and Planning Unit of the Big Deal Police Department. There are 4000 sworn personnel.
PART I. The Chief wants you to measure cynicism of patrol officers and sergeants. He is interested in (a) how cynical each group is, and (b) whether rank is related to cynicism. He is NOT interested in degrees of cynicism – he only wants to distinguish between cynical and not cynical.
1. What is the unit of analysis? 2. How would you select the sample? Why? (include its size) 3. What statistic would you use to summarize the results? 4. Make up data that demonstrates a strong relationship between rank and cynicism 5. Provide summary statistics for each group 6. Prepare a table that displays the above relationship
PART II. When you provide results, the Chief surprises you with another question. Now he wants to know whether gender might be a factor. (This was NOT anticipated when you received your original assignment.)
Your assignment: Using the above data, prepare tables that demonstrate a strong relationship between RANK and CYNICISM, holding GENDER constant.
HOMEWORK EXERCISE  CORRELATION
Hypothesis: Changes in height causes changes in weight
1. Create a scattergram from this data
Height

Weight

71

185

70

210

71

178

68

135

64

123

65

141

72

220

68

137

67

140

67

170

70

130

70

180

68

192

64

145

72

195

62

100

61

110

69

185

68

134

70

235

73

195


2. Does there seem to be a relationship between variables? Is it positive or negative? 3. Provide an estimate of the r statistic 4. Rescale each variable as categorical 5. Use the normal procedure to evaluate an association between categorical variables. Does there still seem to be a relationship?
HOMEWORK  STANDARD ERROR OF THE MEAN & CONFIDENCE INTERVAL
Homework: two random samples of 10 patrol officers from the XYZ Police Department, each officer tested for cynicism (continuous variable, scale 15)
Sample 1 scores: 3 3 3 3 3 3 3 1 2 5
Sample 2 scores: 2 1 1 2 3 3 3 3 4 2
CALCULATE:
Standard deviation for sample 1: _________ (small sample, use n1)
Standard deviation for sample 2: _________ (small sample, use n1)
Standard error of the mean based on sample 1: __________
Standard error of the mean based on sample 2: __________
95% Confidence interval into which the population mean should fall, based on sample 1:
Left limit _____ Right limit ______
95% Confidence interval into which the population mean should fall, based on sample 2:
Left limit _____ Right limit ______
HOMEWORK  DIFFERENCE BETWEEN THE MEANS TEST
Homework: two random samples of 10 patrol officers from the XYZ Police Department, each officer tested for cynicism (continuous variable, scale 15)
Hypothesis 1: Gender determines cynicism
Hypothesis 2: Males are more cynical than females
Sample 1 (males) scores: 3 3 3 3 3 3 3 1 2 5  Variance = .99
Sample 2 (females) scores: 2 1 1 2 3 3 3 3 4 2  Variance = .93
CALCULATE:
Pooled sample variance _______
Standard error of the difference between means _______
t statistic _______
df (degrees of freedom) ________
Hypothesis 1: Would you use a ONEtailed ttest ____ OR a TWOtailed ttest ____ (check ONE only)?
Can you reject the NULL hypothesis? YES ____ NO ____
Hyothesis 2: Would you use a ONEtailed ttest ____ OR a TWOtailed ttest ____ (check ONE only)?
Can you reject the NULL hypothesis? YES ____ NO ____
Instructions for doing a ttest are in the book. The ttest tables are in the appendix.
HOMEWORK  CHISQUARE

Job Stress


Position on police force

Low

High

Total

Sergeant

30

60

90

Patrol officer

86

24

110

Total

116

84

200


1. Calculate expected cell frequencies (null hypothesis of no relationship is true)
2. Compute Chi Square
3. Use table in Appendix E to determine your Chi Square's probability level
4. Can we reject the NULL hypothesis? (As usual, cannot take no more than 5 chances in 100 of being wrong)
HOMEWORK  LOGISTIC REGRESSION
Column b: Logistic regression coefficient reporting relationship between each IV and DV (instigating crime)
Column Exp b: Odds ratio
1. Which independent variable(s) have a statistically significant relationship with the dependent variable? At what level?
2. Interpret Exp(b) for "White" using percentage
3. Interpret Exp(b) for "Number of crime types" using percentage
4. Interpret Exp(b) for "Excitement seeking" using percentage
