- Linear Models
- Box-Cox Transformations, generating Y (pg 324)
- Test for Heteroskedasticity (pg 329)
- Variable Selection (pg 359)
- Ridge Regression/LASSO
- Generalized Linear Models + Logistic Regression
- Model Selection Criteria (Ch. 22)
- Stat 154
- PLSR
- KNN/Kernels
- Discriminant Analysis
- Hierarchal Clustering + Clustering
- Random Forests
- Deep Learning w. Tensorflow or PyTorch
- Data pipeline (k-fold, bagging, etc.)
- implement NestedCV (for all of model selection)
Prioritize LASSO (for variable selection), and model Selection Then everything in Stat154 you think is interesting
- Learn about
- SVM/SVC
- Boosting
- Perceptron
Idea: 1. Cross-validate for hyper-parameters, parameters, etc. 2. Then try bagging/boosting
LDA ESL pg 439
Create correlation matrix for inputs Bayesian hyperparameter tuning