We propose a model-selection method to systematically evaluate the contribution to asset
pricing of any new factor, above and beyond what a high-dimensional set of existing factors
explains. Our methodology explicitly accounts for potential model-selection mistakes, unlike the
standard approaches that assume perfect variable selection, which rarely occurs in practice and
produces a bias due to the omitted variables. We apply our procedure to a set of factors recently
discovered in the literature. While most of these new factors are found to be redundant relative
to the existing factors, a few | such as protability | have statistically signicant explanatory
power beyond the hundreds of factors proposed in the past. In addition, we show that our
estimates and their signicance are stable, whereas the model selected by simple LASSO is not.
%0 Generic
%1 feng2019taming
%A Feng, Guanhao
%A Giglio, Stefano
%A Xiu, Dacheng
%D 2019
%K lasso pca sdf zoo-factor
%T Taming the Factor Zoo: A Test of New Factors
%X We propose a model-selection method to systematically evaluate the contribution to asset
pricing of any new factor, above and beyond what a high-dimensional set of existing factors
explains. Our methodology explicitly accounts for potential model-selection mistakes, unlike the
standard approaches that assume perfect variable selection, which rarely occurs in practice and
produces a bias due to the omitted variables. We apply our procedure to a set of factors recently
discovered in the literature. While most of these new factors are found to be redundant relative
to the existing factors, a few | such as protability | have statistically signicant explanatory
power beyond the hundreds of factors proposed in the past. In addition, we show that our
estimates and their signicance are stable, whereas the model selected by simple LASSO is not.
@preprint{feng2019taming,
abstract = {We propose a model-selection method to systematically evaluate the contribution to asset
pricing of any new factor, above and beyond what a high-dimensional set of existing factors
explains. Our methodology explicitly accounts for potential model-selection mistakes, unlike the
standard approaches that assume perfect variable selection, which rarely occurs in practice and
produces a bias due to the omitted variables. We apply our procedure to a set of factors recently
discovered in the literature. While most of these new factors are found to be redundant relative
to the existing factors, a few | such as protability | have statistically signicant explanatory
power beyond the hundreds of factors proposed in the past. In addition, we show that our
estimates and their signicance are stable, whereas the model selected by simple LASSO is not.},
added-at = {2019-02-26T17:32:41.000+0100},
author = {Feng, Guanhao and Giglio, Stefano and Xiu, Dacheng},
biburl = {https://www.bibsonomy.org/bibtex/238da59832c261a6b3715324045c136ad/antoinefalck},
interhash = {bdbc29b4000aff318d5919643aabf878},
intrahash = {38da59832c261a6b3715324045c136ad},
keywords = {lasso pca sdf zoo-factor},
timestamp = {2019-03-06T20:45:11.000+0100},
title = {Taming the Factor Zoo: A Test of New Factors},
year = 2019
}