Day: February 1, 2021

John Mount thinks about test set size:

In this note we will answer “what is a good test set size?” three ways.

– The usual practical answer.
– A decision theory answer.
– A novel variational answer.

Each of these answers is a bit different, as they are solved in slightly different assumed contexts and optimizing different objectives. Knowing all 3 solutions gives us some perspective on the problem.

My rule of thumb is that I want it to be as small as possible while containing the highest likelihood of hitting all real-world scenarios enough times to provide a valid comparison. This conversely maximizes the size of the training data set, giving us the best chance of seeing the widest variety of scenarios we can during the formative phase.

And as usual, John goes way deeper than my rules of thumb. I like this post a lot.

Comments closed

The easystats team talks about the insight package in R:

We are talking about the insight package. It is what allows other packages, like easystats (parameters, effectsize, performance, report, …) or ggstatsplot, sjstats or modelsummary to be as powerful as they are, supporting tons of different R models. So why make you life hard when you can be like them, and rely on insight?

It is made for developers (and users) that do some postprocessing of different models (e.g., extracting stuff like parameters, values, data, names, specifications, predictions, priors, etc.), whether it is to nicely display their results or to do further computation.

Click through for an example of what it does and how it works. H/T R-bloggers

Comments closed