This episode focuses on high-dimensional linear regression models, specifically discussing causal effects and inference methods. The core of the text explains the Double Lasso procedure, a technique utilizing Lasso regression twice to estimate predictive effects and construct confidence intervals, emphasizing its reliance on Neyman orthogonality for low bias. The authors illustrate its application through examples like the convergence hypothesis in economics and wage gap analysis, comparing its performance against less robust "naive" methods. Furthermore, the text briefly touches upon other Neyman orthogonal approaches, such as Double Selection and Debiased Lasso, and provides references for more in-depth study and related work.DisclosureThe CausalML Book: Chernozhukov, V. & Hansen, C. & Kallus, N. & Spindler, M., & Syrgkanis, V. (2024): Applied Causal Inference Powered by ML and AI. CausalML-book.org; arXiv:2403.02467. Audio summary is generated by Google NotebookLM https://notebooklm.google/The episode art is generated by OpenAI ChatGPT

Ver todos los episodios