1. A sociologist is studying the effect of having children within the first three years of marriage on the divorce rate. From city marriage records she selects a random sample of 400 couples who were married between 1985 and 1990 for the first time, with both members of the couple between 20 and 25. Of the 400 couples, 220 had at least one child within the first three years of marriage. Of the couples who had children, 83 were divorced within 5 years, while in the couples who didn't have children within three years only 52 were divorced. Suppose p1 is the proportion of couples married in this time frame who had a child within the first three years and were divorced within five years; p2 is the proportion of couples married in this time frame who did not have a child within the first two years and were divorced within five years. We would estimate the relative risk of divorce within five years for couples married in this time frame who had a child within the first three years relative to couples married in this time frame who did not have a child within the first two years is

A. 1.30.
B. 0.77.
C. 0.09.

2. Based on surveys conducted in 1989 and 1999, a researcher compared the proportion of high school age females interested in a career in science in 1989 with the proportion in 1999. He concluded that the proportions were not significantly different at the α = 0.05 level because the P-value was 0.121. Assuming the surveys were simple random samples from the appropriate populations, we may conclude

A. that the probability of observing a difference at least as large as that observed by the researcher if, in fact, the two proportions were equal is 0.121.
B. that in repeated sampling, the researcher would obtain the difference actually observed in approximately 12.1% of the samples.
C. very little. Without knowing if the observed difference is practically significant, we cannot assess whether the results are statistically significant.

3. In the race for mayor of Columbus, Ohio, in 1999, one poll found that 61.1% of those surveyed would vote for the Democratic candidate. The poll had a 4.1% margin of error with 95% confidence. We may correctly conclude that

A. there is a 95% probability that the Democratic candidate will receive the majority of the vote because the interval does not include 50%.
B. if the poll were repeated many times and a 95% confidence interval computed for each, approximately 95% of these would show the Democratic candidate to have the majority of the vote.
C. if the poll were repeated many times and a 95% confidence interval computed for each, approximately 95% of these would include the true percentage of the population that would vote for the Democratic candidate.