Jove
Visualize
Contact Us

Related Experiment Videos

Recovery of inter-block information in cross-over trials.

E M Chi1

  • 1Marion Merrell Dow, Cincinnati, OH 45215.

Statistics in Medicine
|July 1, 1991
PubMed
Summary

This study demonstrates recovering treatment effects in cross-over designs using inter-block analysis, similar to incomplete block designs. Combining intra- and inter-block estimates yields generalized least squares for robust analysis.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

M-estimation in cross-over trials.

Biometrics·1994
Same author

Analysis of variance for repeated measures. Data: a generalized estimating equations approach.

Statistics in medicine·1992
Same author

Effects of probucol on plasma lipids, lipoproteins and parameters of high density lipoprotein metabolism.

Hormone and metabolic research = Hormon- und Stoffwechselforschung = Hormones et metabolisme·1992
Same author

Attenuation of atherosclerosis in a modified strain of hypercholesterolemic Watanabe rabbits with use of a probucol analogue (MDL 29,311) that does not lower serum cholesterol.

Arteriosclerosis and thrombosis : a journal of vascular biology·1991
Same author

NMDA receptor complex antagonists have potential anxiolytic effects as measured with separation-induced ultrasonic vocalizations.

European journal of pharmacology·1991
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Area of Science:

  • Biostatistics
  • Clinical Trial Design
  • Statistical Modeling

Background:

  • Cross-over designs are widely used in clinical trials.
  • Analyzing treatment effects in cross-over trials can be complex.
  • Standard methods may not fully utilize all available information.

Purpose of the Study:

  • To demonstrate the recovery of direct and residual treatment effects in cross-over designs.
  • To propose a method combining intra- and inter-block analyses.
  • To provide an efficient estimation approach for cross-over trials.

Main Methods:

  • Utilizing inter-block analysis (patients as blocks) within a cross-over framework.
  • Combining intra-block and inter-block estimates.
  • Calculating generalized least squares estimates.

Main Results:

  • Information on direct and residual treatment effects can be recovered from inter-block analysis.
  • The combination of intra- and inter-block estimates provides the generalized least squares estimate.
  • The proposed approach is recommended when the between-patient variance component is efficiently estimated.

Conclusions:

  • Inter-block analysis offers valuable insights into treatment effects in cross-over designs.
  • Generalized least squares estimation by combining intra- and inter-block estimates is a powerful approach.
  • Efficient estimation of the between-patient variance is crucial for the recommended method's success.

Related Experiment Videos