LASSO FOR PREDICTION AND MODEL SELECTION

• Lasso
• Elastic net
• Square-root lasso
• Continuous, binary, count, and survival-time outcomes
• Clustered data

 

LASSO FOR INFERENCE

• Effect estimates for covariates of interest
• Coefficients, SEs, tests, confidence intervals
• Robust and cluster–robust SEs
• Lasso selects control variables
• Robust to model-selection mistakes by lasso
• Double selection
• Partialing out
• Cross-fit partialing out
• Double machine learning (DML1 and DML2)
• Linear, logit, and Poisson regression
• Endogenous covariates in linear models
• Causal inference/Treatment effects

 

BAYESIAN LASSO

 

DATA PREPARATION

• Divide data into random samples
• Manage large lists of variables
  • Create names for referring to
    • All continuous variables
    • All categorical variables
    • Your own variable groupings

 

© Copyright 1996–2024 StataCorp LLC. All rights reserved.

SELECTION METHODS

• Cross-validation
• Adaptive lasso
• Plugin iterative formula
• Bayesian information criterion (BIC)
• Select your own

 

EVALUATE SELECTED MODEL

• Graphs
  • Cross-validation function plot
  • Coefficient paths
• Goodness of fit
  • Mean squared error of prediction
  • In-sample and out-of-sample R-squareds
  • Deviance
  • In-sample and out-of-sample deviance ratios
  • BIC
  • Relative L1-norm of coefficients
  • Relative L2-norm squared of coefficients
• Estimated coefficients
  • Penalized
  • Postselection