10class.wk6 - PubH 5-462 Clinical Trials: Readings for Week...

Info iconThis preview shows pages 1–4. Sign up to view the full content.

View Full Document Right Arrow Icon
PubH 5-462 Clinical Trials: Readings for Week 6 Friedman, Furberg, and DeMets. Fundamentals of Clinical Trials. Chapter 4. Supplemental Reading/References 1. Pocock, S.J.: Clinical Trials: A Practical Approach. John Wiley and Sons, Ltd., Chapter 8. 2. Hills, M., Armitage P. The two-period cross-over clinical trial. Br. J Clin Pharmacology , 8, 7-20, 1979. 3. Byar, D.P. et al. Design considerations for AIDS trials. NEJM , 323:1343-1348, 1990. 4. Lubsen J, Pocock SJ. Factorial designs in cardiology: pros and cons. European Heart Journal 15:585-588, 1994. 5. Larntz K, et al. Data analysis issues for protocols with overlapping enrollment. Stat Med , 15:2445-2453, 1996. 6. McAllister FA et al. Analysis and reporting of factorial trials. JAMA 289:2545- 2553, 2003. 1
Background image of page 1

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

View Full DocumentRight Arrow Icon
Common Designs for Controlled Clinical Trials A. Parallel comparisons of treatments - each patient receives only one of the treatments. The treatment(s) to be received is determined by a random process. 1. The required sample size for this type of study depends on the amount of variability between patients in the primary response variable, the expected treatment difference and Type I and Type II error rates. 2. The simplest form of this design is the when randomization is carried out without regard to prognostic variables. 3. Since, by chance, differences in baseline characteristics could occur in such designs, stratification frequently is employed in the design; post-stratification on important baseline factors is almost always carried out to some extent. Lavori (Designs for experiments-parallel comparisons of treatments, on Medical Uses of Statistics, 1986) described 35 randomized clinical trials published in the NEJM involving parallel comparisons of treatments. Twenty-two controlled for covariates in the analysis. 4. When prognostic factors are controlled by blocking or matching individual patients, the study is sometimes termed a randomized block experiment . One example of a randomized block study is the matched pairs study where each pair constitutes a block. 5. If there are several separate factors to be assessed, then a factorial design may be used. The principal advantage of this design is that there is the potential to answer more than one question in the same experiment. The study may, however, be more complex to carry out since if 3 factors are to be compared at 2 levels each, patients must be randomly assigned to one of 8 possible treatment combinations. Recently, several people have argued that 2
Background image of page 2
this design should be utilized more often. Situations when the factorial design may be particularly useful: 1) there is interest in studying multiple treatments (e.g., pain from peripheral neuropathy), and when there is an interest in their interaction. 2)
Background image of page 3

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

View Full DocumentRight Arrow Icon
Image of page 4
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 / 20

10class.wk6 - PubH 5-462 Clinical Trials: Readings for Week...

This preview shows document pages 1 - 4. Sign up to view the full document.

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