Models with high-dimensional covariates arise frequently in economics and other fields. Often, only a few covariates have important effects on the dependent variable. When this happens, the model is said to be sparse. In applications, however, it is not known which covariates are important and which are not. This paper reviews methods for discriminating between important and unimportant covariates with particular attention given to methods that discriminate correctly with probability approaching 1 as the sample size increases. Methods are available for a wide variety of linear, nonlinear, semiparametric and nonparametric models. The performance of some of these methods in finite samples is illustrated through Monte Carlo simulations and an empirical example.
Authors
Northwestern University
Journal article details
- DOI
- 10.1111/caje.12130
- Publisher
- Wiley Online Library
- Issue
- Volume 48, Issue 2, May 2015
Suggested citation
Horowitz, J. (2015). 'Variable selection and estimation in high-dimensional models' 48(2/2015)
More from IFS
Understand this issue
Council funding is a numbers game in which everybody is losing
13 May 2024
Empty defence spending promises are a shot in the dark
29 April 2024
Public investment: what you need to know
25 April 2024
Policy analysis
The past and future of UK health spending
14 May 2024
NHS spending has risen less quickly than was planned at the last election, despite the pandemic and record waiting lists
14 May 2024
Recent trends in and the outlook for health-related benefits
19 April 2024
Academic research
The employment and distributional impacts of nationwide minimum wage changes
10 April 2024
Willingness to pay for improved public education and public healthcare systems: the role of income mobility prospects
14 March 2024
Unfunded mandates and taxation
14 March 2024