A couple of months ago I came across this paper, “Bias, precision and statistical power of analysis of covariance in the analysis of randomized trials with baseline imbalance: a simulation study”, published in the open access online journal BMC Medical Research Methodology, by Egbewale, Lewis and Sim. Using simulation studies, as the title says, the authors investigate the bias, precision and power of three analysis methods for a randomized trial with a continuous outcome and a baseline measure of the same variable, when there is an imbalance at baseline in the baseline measure. The three methods considered are ANOVA (a two-sample t-test here), an analysis of change (CSA, change from baseline to follow-up) scores, and analysis of covariance (ANCOVA), which corresponds to fitting a linear regression model with outcome measurement as the dependent variable, with randomized treatment and baseline measure as covariates.
Jonathan Bartlett
Test for Alzheimer’s (allegedly) no better than a coin toss
From a tweet I just came across the following article at the UK’s NHS Choices website. It raises doubts about the predictive value of a new test for Alzheimer’s disease, published in a paper here. The model aims to predict whether those suffering from mild cognitive impairment will progress to Alzheimer’s disease (AD) in the following year.
Robustness to misspecification when adjusting for baseline in RCTs
It is well known that adjusting for one or more baseline covariates can increase statistical power in randomized controlled trials. One reason that adjusted analyses are not used more widely may be because researchers may be concerned that results may be biased if the baseline covariate(s)’ effects are not modelled correctly in the regression model for outcome. For example, a continuous baseline covariate would by default be entered linearly in a regression model, but in truth it’s effect on outcome may be non-linear. In this post we’ll review an important result which shows that for continuous outcomes modelled with linear regression, this does not matter in terms of bias – we obtain unbiased estimates of treatment effect even if we mis-specify a baseline covariate’s effect on outcome.