Christopher Louden implements your data science and statistics projects.
On Rising Up Against Statistical Significance
Valentin Amrhein, Sander Greenland, and Blake McShane write in Nature that because people often have a poor grasp of the concept of a p-value or the meaning of statistical significance, that we should stop categorizing results as statistically significant or non-statistically significant and replacing statistical significance with confidence intervals. While I agree with their goal, I think that we should be more careful in our solution to the problem.
What I Would Like to See in a Type System
I want a type system that allows me to put a lot of detail into what the data I am expecting should look like. I want a type system that can help me detect data with impossible values at the earliest possible moment (such as a negative age or age over 200). That is simply not possible when working with languages that restrict you to integers, floats, strings, etc.
The Ethics of Study Design
Because including humans (and animals) in a clinical trial exposes them to risk, we must design all aspects of the clinical trial ethically. Others can better discuss how consent, protection of protected populations and similar topics should be handled. I want to focus instead on how the statistical design of a clinical trial impacts the ethics of the trial.
The Bayesian Approach to Sample Size Calculations
Sample Size determination is generally done using a frequentist approach. However, Bayesian approaches can also be used allowing a researcher to take into account prior information as well as handle uncertainty about parameters used in the frequentist approach.
Using Pilot Studies in Clinical Research
A pilot study is a smaller version of a planned study. The purpose of the pilot study is to test the design of the larger study to improve its likelihood of success. Unfortunately, there are several misconceptions about what a pilot study is for.