Analysis of Preferences in Crossover Designs

Analysis of Preferences in Crossover Designs

In crossover designs for the comparison of two treatments, A and B, each individual receives both treatments in a randomized order. We present a Bayesian solution to the analysis of such designs when each individual states a preference for either A or B. Comparison is made with other analyses of thi...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Biometrics 1981-09, Vol.37 (3), p.575-578
1. Verfasser: Dunsmore, Ian R.
Format: Artikel
Sprache:eng
Schlagworte:
Approximation
Clinical Trials as Topic - methods
Crossovers
Design analysis
Humans
Information relevance
Logistics
Modeling
Proportions
Shorter Communications
Statistical relevance model
Statistics as Topic
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In crossover designs for the comparison of two treatments, A and B, each individual receives both treatments in a randomized order. We present a Bayesian solution to the analysis of such designs when each individual states a preference for either A or B. Comparison is made with other analyses of this case and with the related binary response models of Cox (1958, Biometrika 45, 562-565) and Gart (1969, Biometrika 56, 75-80). An example is given to illustrate that 'no preferences' may provide relevant information.
ISSN:0006-341X
1541-0420
DOI:10.2307/2530570