The two sample t-test is one of the most used statistical procedures. Its purpose is to test the hypothesis that the means of two groups are the same. The test assumes that the variable in question is normally distributed in the two groups. When this assumption is in doubt, the non-parametric Wilcoxon-Mann-Whitney (or rank sum ) test is sometimes suggested as an alternative to the t-test (e.g. the Wikipedia page on the t-test), which doesn’t rely on distributional assumptions. But is this necessarily a good ‘replacement’?
Interpreting changes in hazard and hazard ratios
I recently attended a great course by Odd Aalen, Ornulf Borgan, and Hakon Gjessing, based on their book ’Survival and Event History Analysis: a process point of view’. Among the many interesting topics covered was the issue of how to interpret changes in estimated hazard functions, and similarly, changes in hazard ratios comparing two groups of subjects.
Leveraging baseline covariates for improved efficiency in randomized controlled trials
In a previous post I talked about the issue of covariate adjustment in randomized controlled trials, and the potential for improving the precision of treatment effect estimates. In this post I’ll look at one of the (fairly) recently developed approaches for improving estimates of marginal treatment effects, based on semiparametric theory.