STAT 405 Fall 2014 - Homework 7 (32 pts.) Due Wednesday, October28th

1)Risk of BacteriuriaAmong OC Users and Nonusers
The presence of bacteria in the urine (bacteriuria) has been associated with kidney disease. Conflicting results have been reported from several studies concerning the possible role of oral contraceptives (OCs) in bacteriuria. The following data were collected in a population-based study of non-pregnant premenopausal women younger than age 50.

a)Estimate the crude OR for Bacteriuria (bacteria in the urine) associated with OC use from the overall table. Also estimate the OR for bacteriuria associated with OC use for each age group using the stratified tables. Does age group appear to be a confounding factor? Discuss. (6 pts.)

b)Perform a significance test to examine the association between OC use and bacteriuria after controlling for age. Summarize your findings. (4 pts.)

c)Estimate the ORin favor of bacteriuria for OC users vs. non-OC users after controlling for age. How does this compare to the crude OR calculated in part (a)? (3 pts.)

d)Is the association between bacteriuria and OC use comparable among the different age groups? Conduct an appropriate test. Summarize your findings. (4 pts. BONUS)

2)Fracture Incidence Between Raloxifene and Placebo Treated Women

A study of raloxifene and incidence of fractures was conducted among women with evidence of osteoporosis. The women were initially divided into two groups: those with and those without pre-existing fractures. The women were randomized to raloxifene or placebo and followed for 3 years to determine the incidence of new vertebral fractures, with the results shown in the tables below.

No Pre-existing Fractures

Treatment / New fractures / No new fractures / Row
Totals
Raloxifene / 34 / 1466 / 1500
Placebo / 68 / 1432 / 1500
Column
Totals /
102 /
2898 /
3000

Pre-existing Fractures

Treatment / New fractures / No new fractures / Row
Totals
Raloxifene / 103 / 597 / 700
Placebo / 170 / 630 / 800
Column
Totals /
273 /
1227 /
1500

a)Among those with pre-existing fractures, test whether raloxifene affects the incidence of new fractures. Estimate the OR (with a 95% CI) for a new fracture associated with raloxifene vs. placebo. Discuss these results. (6 pts.)

b)Repeat (a) for those without pre-existing fractures. (6 pts.)

c)Does the presence of pre-existing fractures appear to be a confounding factor? Explain. (3 pts.)

d)Conduct an appropriate test for determining whether an association between raloxifene treatment and new fractures is present controlling for pre-existing fracture status. Summarize your results. (4 pts.)