Elsevier

Animal Behaviour

Volume 63, Issue 4, April 2002, Pages 815-822
Animal Behaviour

Commentaries
Incorrect analysis of crossover trials in animal behaviour research

https://doi.org/10.1006/anbe.2001.1950Get rights and content

References (76)

  • D.Y. Lin

    MULCOX2: a general computer program for the Cox regression analysis of multivariate failure time data

    Computer Methods and Programs in Biomedicine

    (1993)
  • S. Abeyasekera et al.

    The desirability of adjusting for residual effects in a crossover design

    Biometrics

    (1984)
  • A. Agresti

    Categorical Data Analysis

    (1990)
  • A. Agresti

    Distribution-free fitting of logit models with random effects for repeated categorical responses

    Statistics in Medicine

    (1993)
  • P.S. Albert

    Longitudinal data analysis (repeated measures) in clinical trials

    Statistics in Medicine

    (1999)
  • N.T.J. Bailey

    Statistical Methods in Biology

    (1995)
  • J. Bart et al.

    Sampling and Statistical Methods for Behavioral Ecologists

    (1998)
  • M.P. Becker et al.

    Marginal modeling of binary cross-over data

    Biometrics

    (1993)
  • F. Bellavance et al.

    A nonparametric approach to the analysis of three-treatment three-period crossover designs

    Biometrika

    (1995)
  • R.C. Campbell

    Statistics for Biologists

    (1989)
  • D. Collett

    Modelling Survival Data in Medical Research

    (1994)
  • M.J. Crawley

    GLIM for Ecologists

    (1993)
  • M.J. Crowder et al.

    Analysis of Repeated Measures

    (1990)
  • R. Dı́az-Uriarte

    Anti-predator behaviour changes following an aggressive encounter in the lizard Tropidurus hispidus

    Proceedings of the Royal Society of London, Series B

    (1999)
  • Dı́az-Uriarte, R. 2001, The analysis of cross-over trials in animal behavior experiments: review and guide to the...
  • P.J. Diggle et al.

    Analysis of Longitudinal Data

    (1994)
  • A.J. Dobson

    An Introduction to Generalized Linear Models

    (1990)
  • A.N. Donev

    Crossover designs with correlated observations

    Journal of Biopharmaceutical Statistics

    (1998)
  • E.S. Edgington

    Randomization Tests

    (1995)
  • R.K. Elswick et al.

    A nonparametric approach to the analysis of the 2-treatment, 2-period, 4-sequence crossover model

    Biometrics

    (1989)
  • F. Ezzet et al.

    A random effects model for ordinal responses from a crossover trial

    Statistics in Medicine

    (1991)
  • F. Ezzet et al.

    A random effects model for ordinal responses from a crossover trial: Reply

    Statistics in Medicine

    (1993)
  • M. Feingold et al.

    Cross-over trials with censored data

    Statistics in Medicine

    (1996)
  • V. Fidler

    Change-over clinical trial with binary data: mixed-model-based comparison of tests

    Biometrics

    (1984)
  • A.T. Galecki

    General class of covariance structures for two or more repeated factors in longitudinal data analysis

    Communications in Statistics. Theory and Methods

    (1994)
  • J.M. Grender et al.

    Analysis of crossover designs with multivariate response

    Statistics in Medicine

    (1993)
  • A. Grieve et al.

    Estimating treatment effects in clinical crossover trials

    Journal of Biopharmaceutical Statistics

    (1998)
  • K.B. Hafner et al.

    Some analysis strategies for three-period changeover designs with two treatments

    Statistics in Medicine

    (1988)
  • N.J. Horton et al.

    Review of software to fit Generalized Estimating Equation regression models

    American Statistician

    (1999)
  • P. Hougaard

    Analysis of Multivariate Survival Data

    (2000)
  • W.D. Johnson et al.

    Multivariate nonparametric analysis for the two-period crossover design with application in clinical trials

    Journal of Biopharmaceutical Statistics

    (1993)
  • W.D. Johnson et al.

    Analyzing multivariate data in crossover designs using permutation tests

    Journal of Biopharmaceutical Statistics

    (1996)
  • B. Jones et al.

    Modelling and design of cross-over trials

    Statistics in Medicine

    (1996)
  • B. Jones et al.

    Design and Analysis of Cross-Over Trials

    (1989)
  • B. Jones et al.

    Comments on ‘Estimating treatment effects in clinical crossover trials’

    Journal of Biopharmaceutical Statistics

    (1998)
  • J.W. Jung et al.

    Multivariate non-parametric methods for Mann-Whitney statistics to analyse cross-over studies with two treatment sequences

    Statistics in Medicine

    (1999)
  • J.D. Kalbfleisch et al.

    The Statistical Analysis of Failure Time Data

    (1980)
  • M.G. Kenward et al.

    The analysis of binary and categorical data from crossover trials

    Statistical Methods in Medical Research

    (1994)
  • Cited by (62)

    • Randomised controlled trial of corneal vs. scleral rigid gas permeable contact lenses for keratoconus and other ectatic corneal disorders

      2020, Contact Lens and Anterior Eye
      Citation Excerpt :

      In a crossover design the analysis should take account of the period and sequence effects, which may be confounded with treatment effects, [53,54]. It is reasonable to assume that randomisation minimises sequence effects: the period effect must be accounted for due to possible changes of the participants during the intervals between the measurements, or through habituation to the measurement itself [55]. The possibility of a differential carryover effect must also be accounted for, although it is unlikely in chronic conditions such as keratoconus, under non-curative management, such as contact lenses and with the incorporation of a washout period [53,54].

    • Combined effects of nocturnal exposure to artificial light and habitat complexity on fish foraging

      2019, Science of the Total Environment
      Citation Excerpt :

      Hence, only the disturbed light cycle treatments were used for behavioural analyses. To determine factors affecting fish consumption (log-transformed numbers of consumed gammarids) we applied a General Linear Mixed Model (GLMM) for cross-over designs as per Díaz-Uriarte (2002) and Jones and Kenward (2003). The following factors were included in the model: (1) ‘Light cycle’, a between-subject fixed factor indicating the presence or absence of artificial light at night; (2) ‘Habitat type’, a between-subject fixed factor indicating a habitat type (sandy substratum or woody debris); (3) ‘Period’, a within-subject fixed factor adjusted for time of the day, indicating the first or second period during each trial (to show the effect of passing time on fish responses); (4) ‘Sequence’, a between-subject fixed factor referring to the sequence of periods (dusk/night or night/dusk); (5) ‘Time of the day’, a within-subject fixed factor adjusted for period (dusk or night) and (6) fish individual as a random factor.

    View all citing articles on Scopus
    f1

    Correspondence and present address: R. Dı́az-Uriarte, Navacerrada 37, 28430 Alpedrete, Madrid, Spain (email:[email protected] ).

    View full text