Chapters 10 & 11 Question 3 (5 points) A drug company maintains that a new drug G for a certain disease has a 50% cure rate as compared with drug H, which has only a 25% cure rate. You are asked to design a clinical trial comparing drugs G and H. Using the following table, estimate the number of patients needed in each therapy group to detect such a difference with alpha=0.05, two-sided, and beta=0.20. Number of Patients Needed in an Experimental and a Control Group for a Given Probability of Obtaining a Significant Result (Two-Sided Test) DIFFERENCES IN THE CURE RATES BETWEEN THE TWO TREATMENT GROUPS Lower of the Two Cure Rates 0.05 0.10 0.15 0.20 0.25 0.30 0.05 420 130 69 44 36 31 0.10 680 195 96 59 41 35 0.15 910 250 120 71 48 39 0.20 1,090 290 135 80 53 42 0.25 1,250 330 150 88 57 44 0.30 1,380 360 160 93 60 44 0.35 1,470 370 170 96 61 44 0.40 1,530 390 175 97 61 44 a = 0.05: power (1 - B) = 0.80. Data from Gehan E. Clinical trials in cancer research. Environ Health Perspecti Question 4 (10 points) A randomized controlled trial is testing whether Drug A reduces the likelihood of stroke recurrence than the current standard of care. In the trial, 300 stroke patients are randomized into two groups where Group 1 receives Drug A, and Group 2 receives the standard of care. The investigator compared the cumulative incidence of a recurrent stroke between both groups. Some patients randomized to standard of care obtain Drug A through other means. Meanwhile, some participants randomized to Drug A ended up not taking it. The results from the randomized controlled trials are below: GROUP 1 GROUP 2 RANDOMIZED TO DRUG A RANDOMIZED TO STANDARD OF CARE Took Drug A Standard of Care Took Drug A Standard of Care Had a recurrent stroke 10 20 40 Did not have a recurrent stroke 80 40 15 90 4A. With an intention-to-treat analysis, calculate the cumulative incidence ratio for recurrent stroke using standard of care as the reference. Answers should be rounded to two decimal places (HINT: with the ITT approach, all randomized patients are included in the analysis, based on the groups to which they were initially randomly assigned 4B. With a per-protocol analysis, calculate the cumulative incidence ratio for recurrent stroke using standard of care as the reference. Answers should be rounded to two decimal places. (HINT: per-protocol only analyzes data from participants who followed protocol, excluding their data after they become nonadherent)