What I built
- 01Insurance CSV1,338 policyholders
- 02R nested modelsNested models, then a smoker × obese interaction
- Linear regression
- Interaction effects and confounding
- R
- 03Python / pandas
- 04scikit-learn CVLinear model matched ridge, lasso and random forest
- Cross-validation
- scikit-learn
- 05Subgroup errorsError differs a lot by subgroup
- Subgroup error analysis