Question

Let us continue with analyses of data from the study of M Daviglus et al (N Engl J Med 1997) on the relationship of fish consumption with death from coronary heart disease (CHD) among 1,822 male employees of the Western Electric Company Hawthorne Works in Chicago who were followed for 30 years.

2. Daviglus and colleagues also reported the follow-up time in these men. The 242 men who consumed at least 35 g/day of fish were followed for a total of 6,368 person-years. As indicated in question 1, 46 of these 242 men died of CHD over this follow-up period.

a. Provide a point estimate and an appropriate 95% confidence interval for the rate of CHD death in these men. Additionally provide a brief interpretation of your confidence interval.

b. Perform a one-sample test to determine whether the observed rate is significantly different from 10 events per 1,000 person-years. Make sure to specify your null and alternative hypotheses and give a brief conclusion.

c. Suppose you only followed a 10% sample of these 242 men and observed 5 CHD deaths in 637 person-years. Construct and interpret a 95% confidence interval for the rate of CHD death with these data.

Answer 1