Crossover Experiment

From GM-RKB
(Redirected from cross-over experiment)
Jump to navigation Jump to search

A Crossover Experiment is a repeated measures experiment with two experiment groups where the groups swap treatments at some time period.



References

2013a

  1. Jones, Byron; Kenward, Michael G. (2003). Design and Analysis of Cross-Over Trials (Second ed.). London: Chapman and Hall. 
  2. Vonesh, Edward F.; Chinchilli, Vernon G. (1997). "Crossover Experiments". Linear and Nonlinear Models for the Analysis of Repeated Measurements. London: Chapman and Hall. pp. 111–202. 

2013b

2013c

  1. Vonesh & Chinchilli (1997)
  2. Jones & Kenward (2003)

2003

  • (Jones & Kenward, 2003) ⇒ Byron Jones, and Michael G Kenward. (2003). “Design and Analysis of Cross over Trials." CRC Press. ISBN:0412606402
    • QUOTE: This book is concerned with a particular sort of comparative trial known as the cross-over trial in which subjects receive different sequences of treatments. …

      For a cross-over trial we will denote by [math]\displaystyle{ t }[/math], [math]\displaystyle{ p }[/math] and [math]\displaystyle{ s }[/math], respectively, the number of treatments, periods and sequences. So for example, in a trial in which each subject received three treatments A, B and C, in one of the six sequences: ABC, ACB, BAC, BCA, CAB and CBA, we have [math]\displaystyle{ t }[/math]=3, [math]\displaystyle{ p }[/math]=3 and [math]\displaystyle{ s }[/math]=6. In general, we denote by [math]\displaystyle{ y_{ijk} }[/math] the response observed on the [math]\displaystyle{ k }[/math]th subject in period [math]\displaystyle{ j }[/math] of sequence group [math]\displaystyle{ i }[/math]. It is assumed that [math]\displaystyle{ n_i }[/math] subjects are in sequence group [math]\displaystyle{ i }[/math].