Large-P Variable Selection in Two-Stage Models

2020/03/23 by Haim Bar, Bar, Haim, Kangyan Liu +1
Engineering · Mathematics · #Applications (stat.AP) #Control Systems and Identification #FOS: Computer and information sciences #Fault Detection and Control Systems #Statistical Methods and Inference

paper · pdf · doi:10.48550/arxiv.2003.10484

openalex publication_date 2020/03/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Model selection in the large-P small-N scenario is discussed in the framework of two-stage models. Two specific models are considered, namely, two-stage least squares (TSLS) involving instrumental variables (IVs), and mediation models. In both cases, the number of putative variables (e.g. instruments or mediators) is large, but only a small subset should be included in the two-stage model. We use two variable selection methods which are designed for high-dimensional settings, and compare their performance in terms of their ability to find the true IVs or mediators. Our approach is demonstrated via simulations and case studies.

Citations

• The moderator-mediator variable distinction in social psychological research: Conceptual, strategic, and statistical considerations.
• Limited information estimators and exogeneity tests for simultaneous probit models
• Statistical mediation analysis with a multicategorical independent variable
• Least angle regression

Related

• A Scalable Empirical Bayes Approach to Variable Selection
• Identifying important predictors in large data bases -- multiple testing and model selection
• Beyond Support in Two-Stage Variable Selection
• Bayesian variable selection in high dimensional problems without assumptions on prior model probabilities
• Post-Selection and Post-Regularization Inference in Linear Models with Many Controls and Instruments