High Statistical Power Can Be Deceiving

Most studies aim to achieve high statistical power and precision by increasing sample sizes. Many researchers will conclude that there is no effect if they get a nonsignificant result in a high-powered study. In this post, I discuss why this is incorrect.

Meta-Analysis: Choose Your Model Wisely

Meta-analyses are incredibly common in the literature and they can be hard to understand. In this post, I explain why we conduct meta-analyses in the first place, the effects of different assumptions on the calculations, and traps to avoid when choosing a model.

Myth: Covariates Need to Be Balanced in RCTs

Many people believe that the purpose of randomization is to perfectly balance out both known and unknown covariates in order to reach causal inferences, however, this is simply not true and is a misunderstanding of the process of randomization.