A prerandomization assessment of an efficacy variable is often used as a covariate in the analysis to perform between-treatment comparisons. Such assessments may be made more than once. The variable to be used as the covariate must be chosen prior to any analyses. This choice may be the use of both assessments as covariates. The impact of the choice is examined here.
CochranWG. Analysis of covariance: its nature and uses. Biometrics.1957;13:261–281.
2.
TuDShalayKPaterJ. Adjustment of treatment effect for covariates in clinical trials: statistical and clinical issues. Drug Inf J.2000;34:511–523.
3.
AssmannSFPocockSJEnosLEKastenLE. Subgroup analysis and other (mis)uses of baseline data in clinical trials. Lancet.2000:355:1064–1069.
4.
PocockSJAssmannSFEnosLEKastenLE. Subgroup analysis, covariate adjustment, and baseline comparison in clinical trial reporting: current practices and problems. Stat Med.2002:21:2917–930.
5.
BergerVW. A novel criterion for selecting covariates. Drug Inf J.2005;39:233–241.
6.
GlueckDHMullerKE. Adjusting power for a baseline covariate in linear models. Stat Med.2003;22:2535–2551.
7.
FordINorrieJ. The role of covariates in estimating treatment effects and risk in long-term clinical trials. Stat Med.2002;21:2899–2908.
8.
International Conference on Harmonisation.ICH E9; Statistical Principles for Clinical Trials. 63 Federal Register49584–49598 (1998).
9.
TempleRJ. Special study designs: early escape, enrichment, studies in non-responders. Commun Stat Theory Meth.1994;23:499–531.
10.
LeberPDDavisCS. Threats to the validity of clinical trials employing enrichment strategies for sample selection. Control Clin Trials.1998;19:178–187.
