hw1key - Assignment#1 Key Clinical Trials(100 points Due...

Info iconThis preview shows pages 1–3. Sign up to view the full content.

View Full Document Right Arrow Icon
Assignment #1 Key Clinical Trials (100 points) Due February 10, 2011 1. (5) In clinical research studies it is important to control confounding factors in the design and/or analysis of the investigation. List 3 methods that are used to control/eliminate confounding. For each, give an example of a study that used the specific method. You can use examples from the class lectures. Answer: Design- Randomization as in the AMIS study comparing aspirin versus placebo Stratification Matching as in coffee and CHD case control study Analysis- Post stratification as in gender and PCP study – stratification on CD4+ count Regression analysis as in type a behavior and CHD study 2. (5) In a recently reported trial among patients with metastatic melanoma 676 patients were randomized in a 3:1:1 ratio to receive ipilimumab plus a gp100 peptide vaccine, ipilimumab plus placebo for gp100, or the gp100 vaccine plus placebo for ipilimumab. Assuming the randomization worked as planned, approximately how many patients would you expect there be in each treatment group? Answer: ipilimumab plus a gp100 = 676*3/5 = 406 ipilimumab plus placebo = 676*1/5 = 135 gp100 plus placebo = 676*1/5 = 135 3. (15) In a recent clinical trial of three mechanical heart valves, one valve (Edwards-Duromedics) was used on even operation days; one valve (Bjork-Shiley) was used on odd operation days when the patient's year of birth was an even one; the third valve (Medtronic-Hall) was used on odd operation days when the patient's year of birth was an odd one. a. (5) Did this study employ an appropriate method to assign treatments? Comment on “allocation concealment”. Answer: No, it is not an appropriate randomization scheme. Because assignments were assigned systematically and not randomily. As a consequence, it is predictable, so participants and investigators can figure out what the group they will be in. This could bias the study. b. (5) What is the desired allocation ratio for this study based on the above description? Answer: Desired allocation ratio of Edwards-Duromedics: Bjork-Shiley: Medtronic-Hall is 2:1:1. c. (5) Describe how you would use simple randomization to generate treatment assignments for this study to obtain the desired allocation ratio. Answer: Generate a random integer from 1 to 4 where each number has an equal probability of being generated. If the number is 1 or 2, then assign Edwards-Duromedics treatment. If the number is 3, then assign Bjork-Shiley treatment. Otherwise, assign Medtronic-Hall treatment. 4. (20) A study of 20 patients scheduled for orthopedic surgery are to be randomized to a surgical ointment (murpirocin) or placebo the day before surgery. The goal of this pilot study is to determine if murpirocin can eradicate Staphylococcus aureus nasal carriage prior to surgery.
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
a. (10) Using the table of random numbers shown in the class slides, prepare a randomization schedule for the study using simple randomization. Describe how you did it in 1 or 2 sentences. Answer:
Background image of page 2
Image of page 3
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 11/21/2011 for the course PUBH 7420 taught by Professor Ph7420 during the Spring '07 term at Minnesota.

Page1 / 6

hw1key - Assignment#1 Key Clinical Trials(100 points Due...

This preview shows document pages 1 - 3. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online