Interpretable Sparse Proximate Factors for Large Dimensions
Bibliographic Data
| ID | 19419949 |
|---|---|
| Authors | Markus Pelger (0000-0001-7111-3588, Stanford University, corresponding author), Ruoxuan Xiong (0000-0002-3701-4428, Stanford University) |
| Year | 2022 |
| Volume | 40 |
| Issue | 4 |
| Pages | 1642-1664 |
| Publication date | 2022-10-02 |
| Open Access | No |
| Type | ARTICLE |
| Venue | Journal of Business and Economic Statistics (JOURNAL) |
| Journal identifiers | ISSN: 0735-0015 • E-ISSN: 1537-2707 |
| Publisher | Informa UK Limited (PUBLISHER • GB) |
| DOI | 10.1080/07350015.2021.1961786 |
| OpenAlex | W3197128176 |
| Language | EN |
| Citations received | 4 |
| References cited | 49 |
This article proposes sparse and easy-to-interpret proximate factors to approximate statistical latent factors. Latent factors in a large-dimensional factor model can be estimated by principal component analysis (PCA), but are usually hard to interpret. We obtain proximate factors that are easier to interpret by shrinking the PCA factor weights and setting them to zero except for the largest absolute ones. We show that proximate factors constructed with only 5%–10% of the data are usually sufficient to almost perfectly replicate the population and PCA factors without actually assuming a sparse structure in the weights or loadings. Using extreme value theory we explain why sparse proximate factors can be substitutes for non-sparse PCA factors. We derive analytical asymptotic bounds for the correlation of appropriately rotated proximate factors with the population factors. These bounds provide guidance on how to construct the proximate factors. In simulations and empirical analyses of financial portfolio and macroeconomic data, we illustrate that sparse proximate factors are close substitutes for PCA factors with average correlations of around 97.5%, while being interpretable
Biology · Econometrics · Factor analysis · Population · Principal component analysis · Proximate · Statistics · Complex Systems and Time Series Analysis · Computer Science · Financial Risk and Volatility Modeling · Mathematics · Monetary Policy and Economic Impact · Applied Mathematics · Artificial Intelligence
An Introduction to Statistical Modeling of Extreme Values
Regularization and Variable Selection Via the Elastic Net
Weak and strong cross‐section dependence and estimation of large panels
Determining the Number of Factors in Approximate Factor Models
Inferential Theory for Factor Models of Large Dimensions
Forecasting Using Principal Components From a Large Number of Predictors
Confidence Intervals for Diffusion Index Forecasts and Inference for Factor-Augmented Regressions
The Varimax Criterion for Analytic Rotation in Factor Analysis
Regression Shrinkage and Selection Via the Lasso
State-Varying Factor Models of Large Dimensions
Fred-Md
Macroeconomic Forecasting Using Diffusion Indexes
| Citations per year | 1 |
|---|---|
| Citation span | 2022 - 2026 (5) |
| Highly cited | No |