Sparse and Robust Factor Modelling
2011-07-25
Research Paper
This publication is part of collection
| Related Files |
|---|
View PDF Version
(2011-1224.pdf, 0.3MB) |
Factor construction methods are widely used to summarize a large panel of variables by means of a relatively small number of representative factors. We propose a novel factor construction procedure that enjoys the properties of robustness to outliers and of sparsity; that is, having relatively few nonzero factor loadings. Compared to more traditional factor construction methods, we find that this procedure leads to better interpretable factors and to a favorable forecasting performance, both in a Monte Carlo experiment and in two empirical applications to large data sets, one from macroeconomics and one from microeconomics.
Keywords
Classifications using
Journal of Economic Literature (JEL) Classification System
Automatically Extracted Terms
- 0 l 1
- factor
- 0 tukey
- tukey
- 0 l 2
- criterion
- forecasting
- number
- variable
- result
- observation
- price
- loading
- l 2 criterion
- forecast
- method
- table
- outlier
- matrix
- boston housing data
