Herpes simplex virus exposure, and expect under their alternative hypothesis to see an elevated proportion of the cases to have Herpes simplex virus exposure, with an odds ratio of 1.4. a. Calculate the power for detecting an effect this large for a one-sided test of size .025. b. Suppose that the investigators wanted 80% power under the above alternative, and planned to use the same number of cases and controls. How many women would be necessary in each group? c. Suppose that the investigators wanted 80% power under the above alternative, and planned to use ten times as many controls as cases. How many women would be necessary in each group? Compare your answer to part (b).
Caroll, Gail, and Lubin (1993) describe a case–control study in which 39 women with
cervical cancer and 76 women without cervical cancer were screened for exposure to
Herpes simplex virus. Investigators expect that roughly 30% of the controls will have
Herpes simplex virus exposure, and expect under their alternative hypothesis to see an
elevated proportion of the cases to have Herpes simplex virus exposure, with an odds
ratio of 1.4.
a. Calculate the power for detecting an effect this large for a one-sided test of size .025.
b. Suppose that the investigators wanted 80% power under the above alternative, and
planned to use the same number of cases and controls. How many women would be
necessary in each group?
c. Suppose that the investigators wanted 80% power under the above alternative, and
planned to use ten times as many controls as cases. How many women would be
necessary in each group? Compare your answer to part (b).
Step by step
Solved in 4 steps with 2 images
