Statistical considerations in the design and analysis of cross-over trials
Date
1991-08
Authors
Advisors
Journal Title
Journal ISSN
ISSN
DOI
Volume Title
Publisher
De Montfort University
Type
Thesis or dissertation
Peer reviewed
Abstract
Cross-over designs are frequently used in clinical trials, usually to compare two treatments. It has long been known that the simple two-period cross-over is adversely affected by the presence of carry-over effects, but it is nevertheless still commonly used. This thesis examines the problems caused by carry-over effects in detail and considers ways of overcoming these problems, either by using a more complex cross-over design, or by carrying out a more sophisticated statistical analysis. Only designs for comparing two treatments are considered, but analysis for continuous and binary variables is covered.
Description
Thesis from Leicester Polytechnic