Вы находитесь на странице: 1из 2

STAT 4006: Categorical Data Analysis Assignment 3 Academic year 13/14, rst term, Chapter 3 Due Date: 5:00

pm Tuesday, 22nd Oct. Assignment box for STAT 4006, 1/F, Lady Shaw Building.

1. Based on murder rates in the United States, the Associated Press reported that the probability a newborn child has of eventually being a murder victim is 0.0263 for nonwhite males, 0.0049 for white males, 0.0072 for nonwhite females, and 0.0023 for white females. a. Find the conditional odds ratios between race and whether a murder victim, given gender. Interpret. b. Find the conditional odds ratios between gender and whether a murder victim, given race. Interpret. c. If half the newborns are of each gender, for each race, nd the marginal odds ratio between race and whether a murder victim. d. If half the newborns are of each gender, for each race, nd the marginal odds ratio between gender and whether a murder victim. e. Does the Simpsons Paradox happen? Explain.

2. In murder trials in 20 Florida counties during 1976 and 1977, the death penalty was given in 23 out of 158 cases in which a white killed a white, in 0 out 11 cases in which a white killed a black, in 13 out of 65 cases in which a black killed a white, and in 4 out of 92 cases in which a black killed a black. a. Exhibit the data as a three-way contingency table. b. Construct the partial tables needed to study the conditional association between defendants race and the death penalty verdict. Compute and interpret the sample conditional odds ratios. c. Compute and interpret the sample marginal odds ratio between defendants race and the death penalty verdict. Do these data exhibit Simpsons paradox?

3. The following table refers to applicants to graduate school at the University of California, Berkeley for the fall 1973 session. Admissions decisions are presented by gender of applicant, for the three largest graduate departments. Denote the three variables by A = whether admitted, G = gender, and D = department. Whether Admitted Male Department 1 2 3 4 5 6 Yes 478 365 117 133 53 22 No 302 199 203 276 138 351 Female Yes 80 16 204 127 94 24 No 23 7 385 250 299 317

(a) Find the sample AG conditional odds ratios, and compare them with the sample AG marginal odds ratio. Why are they so dierent? (b) Conduct the Cochran-Mantel-Haenszel test. Specify the hypothesis and interpret. (c) Calculate and interpret an estimate of the common AG conditional odds ratio.

4. The following table refers to ratings of agricultural extension agents in North Carolina. In each of ve districts, agents were classied by their race and by whether they qualied for a merit pay increase. Blacks, Merit Pay District NC NE NW SE SW Yes 24 10 5 16 7 No 9 3 4 7 4 Whites, Merit Pay Yes 47 45 57 54 59 No 12 8 9 10 12

(a) Find the conditional odds ratios between race and the merit pay decision, given district. Are results similar among districts? (b) Calculate and interpret an estimate of the average conditional association between race and the merit pay decision.

Вам также может понравиться