Abstract
Cross-over trials have the potential to provide large reductions in sample size compared to their parallel groups counterparts. In this chapter, three different types of cross-over design and their analysis will be described. In the linear models used to analyze cross-over data, the variability due to differences between the subjects in the trial may be modeled as either fixed or random effects, and both will be illustrated. In designs of the incomplete block type, where there are more treatments than periods, the use of random subject effects enables between-subject information on the treatment comparisons to be recovered, and how this may be done will also be illustrated. Finally, if the so-called baseline measurements have been taken at the beginning of each treatment period, these can be used as covariates to reduce the variability of the estimated treatment comparisons. The use of baselines will be illustrated using the incomplete block design.
Similar content being viewed by others
References
Altman DG (1991) Practical statistics for medical research. London: Chapman and Hall
Anderson TW, Darling DA (1952) Asymptotic theory of certain “goodness-of-fit” criteria based on stochastic processes. Ann Math Stat 23:193–212
Bretz F, Hothorn T, Westfall P (2016) Multiple comparisons using R. Boca Raton: CRC Press
Chi EM, Reinsel GC (1989) Models for longitudinal data with random effects and AR(1) errors. J Am Stat Assoc 84:452–459
Clark B, Smith D (1981) Introduction to pharmacokinetics. Oxford: Blackwell Scientific Publications
FDA (2013) Guidance for industry: bioequivalence studies and pharmacokinetic endpoints for drugs submitted under an ANDA. Food and Drug Administration
Freeman P (1989) The performance of the two-stage analysis of two treatment, two period crossover trials. Stat Med 8:1421–1432
Grizzle JE (1965) The two-period change-over design and its use in clinical trials. Biometrics 21:467–480
Havliceck LL, Peterson NL (1974) Robustness of the t-test: a guide for researchers on the effect of violations of assumptions. Psychol Rep 34:1095–1114
Hollander M, Wolfe D (1999) Nonparametric statistical methods, 2nd edn. New York: Wiley
Jones B, Kenward MG (2014) Design and analysis of cross-over trials, 3rd edn. Boca Raton: CRC Press
Kenward MG, Roger JH (1997) Small sample inference for fixed effects estimators from restricted maximum likelihood. Biometrics 53:983–997
Patterson HD, Lucas HL (1962) Change-over designs. North Carolina Agricultural Station, Tech Bull 147
Patterson HD, Thompson R (1971) Recovery of inter-block information when block sizes are unequal. Biometrika 58:545–554
Piantadosi S (1997) Clinical Trials. A methodological perspective. New York: Wiley
Rohmeyer K (2014) Crossover. R package Crossover, Version 01-16
Senn S (2006) Change from baseline and analysis of covariance revised. Stat Med 25:4334–4344
Shapiro SS, Wilk MB (1965) An analysis of variance test for normality (complete samples). Biometrika 52:591–611
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Section Editor information
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this entry
Cite this entry
Jones, B. (2021). Cross-over Trials. In: Piantadosi, S., Meinert, C.L. (eds) Principles and Practice of Clinical Trials. Springer, Cham. https://doi.org/10.1007/978-3-319-52677-5_243-1
Download citation
DOI: https://doi.org/10.1007/978-3-319-52677-5_243-1
Received:
Accepted:
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-52677-5
Online ISBN: 978-3-319-52677-5
eBook Packages: Springer Reference MathematicsReference Module Computer Science and Engineering