Back to Search
Start Over
Omitted Variable Bias of Lasso-Based Inference Methods: A Finite Sample Analysis
- Source :
- The Review of Economics and Statistics, vol 105, iss 4
- Publication Year :
- 2023
- Publisher :
- eScholarship, University of California, 2023.
-
Abstract
- We study the finite sample behavior of Lasso-based inference methods such as post double Lasso and debiased Lasso. We show that these methods can exhibit substantial omitted variable biases (OVBs) due to Lasso not selecting relevant controls. This phenomenon can occur even when the coefficients are sparse and the sample size is large and larger than the number of controls. Therefore, relying on the existing asymptotic inference theory can be problematic in empirical applications. We compare the Lasso-based inference methods to modern high-dimensional OLS-based methods and provide practical guidance.<br />Comment: Final author version, accepted at The Review of Economics and Statistics
- Subjects :
- Economics and Econometrics
Economics
Econometrics (econ.EM)
Inference
Mathematics - Statistics Theory
Omitted-variable bias
Sample (statistics)
Statistics Theory (math.ST)
Statistics::Computation
FOS: Economics and business
Statistics::Machine Learning
Lasso (statistics)
Sample size determination
Applied Economics
Statistics
FOS: Mathematics
Statistics::Methodology
Econometrics
Social Sciences (miscellaneous)
Economics - Econometrics
Mathematics
Subjects
Details
- Database :
- OpenAIRE
- Journal :
- The Review of Economics and Statistics, vol 105, iss 4
- Accession number :
- edsair.doi.dedup.....372b30594c3b5d84ca1244777ebccfb1