Why p values aren’t necessary: they are not evidence, and they can’t be replicated

Recently, I reviewed a number of research proposals in which some applied qualitative or mixed (i.e. quantitative and qualitative) methods to answer health questions. I had my “reviewer hat” on as I assessed the proposals for research quality. After 3-4 proposals, it occurred to me that while assessing quantitative research proposals for research quality and reproducible practices was straightforward, doing
Read moreResearch funders are beginning to require that data produced in the course of the research they fund should be made openly available. This is to encourage further discovery and exploration, as well as to extend research questions. In addition, releasing data and code can be in researchers’ interest because it provides a complete and transparent record of how the conclusions
Read moreIn previous posts, we learned that the aim of statistics is to extrapolate properties of samples to make inferences about population. However, random variation in individuals in the population produces sampling error, which means a single sample may not accurately reflect properties of the population. When data are binary, we learned how the 95% confidence interval (CI) of a sample
Read more