Pokemon Individual Recourse
Or how to be the most effective Pokemon trainer
Minimally Sufficient
Recent content on Minimally Sufficient
Latest posts
Assessing Distributions with SIMEX
Noisy observations bias a whole distribution’s tails; SIMEX is an approach for correcting this
Permutation Feature Importance Doesn't Make Sense
It gives arbitrary results when faced with dependent data
Neural Bradley Terry Models
I've got a fever! And the only prescription... is more neural networks.
Non-Transitive Bradley Terry Models
One thing that has always bugged me about Bradley Terry models is that it can't model rock-paper-scissors. Let's see if we can fix that!
Fun with Player Ratings
How to tell who's the best player?
LLM AB Tests
Why get many samples when LLM do trick
Solving Pipes Puzzles with Constraint Propagation
I solve my guilty pleasure puzzle using Julia
Estimating Prevalence using Imperfect Classifiers
How to correct prevalence estimates using PPI
Well-calibrated predictions are not enough
Calibration is an important idea in statistical prediction. However, it’s not the only thing.
Diagnosing Bad Hypothesis Tests
I find a strange plot of p-values from a hypothesis test and investigate.
The Fastest Poisson(1) in the West
How quickly can I generate a Poisson(1) random variable?
Correlation Chains
I investigate SMBC’s novel correlation-chain methodology.
When high variance strategies win
Sometimes you have to take risks if you want to win.
Reservoir Sampling
How do you sample from a stream of unknown length?
March Madness Prediction
I apply a Bradley-Terry model to the NCAA basketball tournament.
Data Splitting
An easy way to perform inference after model selection.