Document Detail

Design and analysis of trials with rare outcomes: examples from trials in herpes transmission and influenza prophylaxis.
MedLine Citation:
PMID:  15911465     Owner:  NLM     Status:  MEDLINE    
For trials with rare outcomes, the number of events to be observed drives the power of the study rather than the proportions of subjects with the event and this is an important consideration when determining sample size. The stratified version of Fisher's exact test was described by Cox as long ago as 1966, but it is only recently that computing power has allowed this to be performed routinely. The issue of stratified analysis can also be addressed through permutation tests and their implementation for multicentre trials where randomisation is stratified by site has potential value. Where the time to event is available, analysis using a proportional hazards model has a potentially valuable role but estimates of differences in proportions are often required particularly for non-inferiority studies and typical software employed for these analyses uses an asymptotic approximation rather than an exact analysis. It is important to assess the impact of missing data on such trials. This can be approached through examination of the pattern of missing data and the covariates predicting discontinuation as well as through sensitivity analysis. Sensitivity analyses need to be done carefully using realistic alternative assumptions and an appealing approach is to impute events for subjects with missing data using the observed placebo rate. Issues of design and analysis for trials with rare outcomes are discussed in the context of two examples-one from a trial designed to investigate transmission of herpes and one that studied prophylaxis of influenza.
Oliver Keene
Related Documents :
7675985 - Characterizing onset in psychopharmacological clinical trials.
7913675 - Interim monitoring of bivariate responses using repeated confidence intervals.
7407775 - Sequential clinical trials in cancer research.
9111615 - Analysis and presentation. clinical trials on prostate cancer.
22016705 - Self-reported exposure to policy and environmental influences on smoking cessation and ...
21565095 - Spatial correlations at different spatial scales are themselves highly correlated in is...
Publication Detail:
Type:  Journal Article    
Journal Detail:
Title:  Contemporary clinical trials     Volume:  26     ISSN:  1551-7144     ISO Abbreviation:  -     Publication Date:  2005 Jun 
Date Detail:
Created Date:  2005-05-24     Completed Date:  2005-11-01     Revised Date:  2007-11-15    
Medline Journal Info:
Nlm Unique ID:  101242342     Medline TA:  Contemp Clin Trials     Country:  United States    
Other Details:
Languages:  eng     Pagination:  311-22     Citation Subset:  IM    
GlaxoSmithKline Research and Development, Greenford Road, Greenford, Middlesex UB6 0HE, UK.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Herpes Genitalis / drug therapy,  transmission
Influenza, Human / prevention & control
Nursing Homes
Proportional Hazards Models
Randomized Controlled Trials as Topic / methods*,  statistics & numerical data
Research Design*
Risk Factors
Sample Size
Sensitivity and Specificity
Sexual Partners
Treatment Outcome*

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine

Previous Document:  Effect of acyclovir on herpetic ocular recurrence using a structural nested model.
Next Document:  Trying to improve the compliance to colorectal cancer screening: a complex study design for a comple...