Robustness of ANCOVA in randomized trials with unequal randomization

Jonathan W. Bartlett

Research output: Contribution to journalArticlepeer-review

3 Citations (SciVal)
201 Downloads (Pure)

Abstract

Randomized trials with continuous outcomes are often analyzed using ANCOVA, with adjustment for prognostic baseline covariates. The ANCOVA estimator of the treatment effect is consistent under arbitrary model misspecification. In an article recently published in the journal, Wang et al proved the model based variance estimator for the treatment effect is also consistent under outcome model misspecification, assuming the probability of randomization to each treatment is 1/2. In this reader reaction we derive explicit expressions which show that when randomization is unequal, the model based variance estimator can be biased upwards or downwards. In contrast, robust sandwich variance estimators can provide asymptotically valid inferences under arbitrary misspecification, even when randomization probabilities are not equal.
Original languageEnglish
Pages (from-to)1036-1038
Number of pages3
JournalBiometrics
Volume76
Issue number3
Early online date10 Dec 2019
DOIs
Publication statusPublished - 10 Sept 2020

Keywords

  • stat.ME

Fingerprint

Dive into the research topics of 'Robustness of ANCOVA in randomized trials with unequal randomization'. Together they form a unique fingerprint.

Cite this