22
EXERCISES EXERCISES • POP QUIZ • POOLING • LOGISTIC REGRESSION

EXERCISES POP QUIZ POOLING LOGISTIC REGRESSION. POP QUIZ

Embed Size (px)

Citation preview

Page 1: EXERCISES POP QUIZ POOLING LOGISTIC REGRESSION. POP QUIZ

EXERCISESEXERCISES

• POP QUIZ• POOLING• LOGISTIC REGRESSION

Page 2: EXERCISES POP QUIZ POOLING LOGISTIC REGRESSION. POP QUIZ

POP QUIZ

Page 3: EXERCISES POP QUIZ POOLING LOGISTIC REGRESSION. POP QUIZ
Page 4: EXERCISES POP QUIZ POOLING LOGISTIC REGRESSION. POP QUIZ
Page 5: EXERCISES POP QUIZ POOLING LOGISTIC REGRESSION. POP QUIZ
Page 6: EXERCISES POP QUIZ POOLING LOGISTIC REGRESSION. POP QUIZ
Page 7: EXERCISES POP QUIZ POOLING LOGISTIC REGRESSION. POP QUIZ
Page 8: EXERCISES POP QUIZ POOLING LOGISTIC REGRESSION. POP QUIZ
Page 9: EXERCISES POP QUIZ POOLING LOGISTIC REGRESSION. POP QUIZ
Page 10: EXERCISES POP QUIZ POOLING LOGISTIC REGRESSION. POP QUIZ
Page 11: EXERCISES POP QUIZ POOLING LOGISTIC REGRESSION. POP QUIZ

Exercises onPooling Exchangeable Matched Strata

Page 12: EXERCISES POP QUIZ POOLING LOGISTIC REGRESSION. POP QUIZ
Page 13: EXERCISES POP QUIZ POOLING LOGISTIC REGRESSION. POP QUIZ
Page 14: EXERCISES POP QUIZ POOLING LOGISTIC REGRESSION. POP QUIZ
Page 15: EXERCISES POP QUIZ POOLING LOGISTIC REGRESSION. POP QUIZ
Page 16: EXERCISES POP QUIZ POOLING LOGISTIC REGRESSION. POP QUIZ
Page 17: EXERCISES POP QUIZ POOLING LOGISTIC REGRESSION. POP QUIZ
Page 18: EXERCISES POP QUIZ POOLING LOGISTIC REGRESSION. POP QUIZ

Exercises on Logistic RegressionFor Matched Data

Page 19: EXERCISES POP QUIZ POOLING LOGISTIC REGRESSION. POP QUIZ
Page 20: EXERCISES POP QUIZ POOLING LOGISTIC REGRESSION. POP QUIZ
Page 21: EXERCISES POP QUIZ POOLING LOGISTIC REGRESSION. POP QUIZ

Answers to Exercises on Pooling Exchangeable Matched Sets1. How many concordant pairs are there where both pair members are exposed? «1»

2. How many concordant pairs are there where both members are unexposed? «1» 3. How many discordant pairs are there where the case is exposed and the control is unexposed? «2»4. How many discordant pairs are there where case is unexposed and the control is exposed? «1» 5. This table is called «McNemar's» table. 6. What is the estimated mOR for these data? «2»7. What type of matched analysis is being used with this table? «unpooled» 8. What is the estimated mOR from these data (use the formula for the mOR in the box below)? «2.5»9. What type of matched analysis is being used here? «pooled»10. Which type of analysis should be preferred for these matched data (where smoking status is the only matched variable), pooled or unpooled? «pooled»11. W= «2»? 12. X = «1»? 13. Y =«0»? 14. Z= «2»?15. mOR (unpooled) = «undefined». 16. mOR (pooled) = «2.5».17. Which of the following helps explain why the pooled mOR estimate should be preferred to the unpooled mOR? a. The pooled mOR's are equal whereas the unpooled mOR's are different. b.The unpooled mOR's assume that exchangeable matched pairs are not unique. c.The pooled mOR's assume that exchangeable matched pairs are unique. «a»

Page 22: EXERCISES POP QUIZ POOLING LOGISTIC REGRESSION. POP QUIZ

Answers to Exercises on Logistic Regression for Matched Data1. Which of the logistic models shown below is appropriate for analyzing these

data? «b»2. What method of estimation should be used to fit the appropriate model for

these data? «Conditional MLE»3. What is the adjusted odds ratio for the effect of SMK on cervical cancer

outcome? «exp(1.4361)» 4. Is number of lifetime sexual partners a significant predictor of cervical cancer

outcome, controlling for the matching variables and the other non-matching variables? «yes»

5. Are the matching variables being controlled? «yes»6. A 95% CI for the (adjusted) effect of SMK is given by the expression «exp[1.4361 +- 1.96(.3167)]»