We construct a robust stochastic discount factor (SDF) that summarizes the joint explanatory
power of a large number of cross-sectional stock return predictors. Our method achieves robust
out-of-sample performance in this high-dimensional setting by imposing an economically
motivated prior on SDF coefficients that shrinks the contributions of low-variance principal
components of the candidate factors. While empirical asset pricing research has focused on SDFs
with a small number of characteristics-based factors—e.g., the four- or five-factor models
discussed in the recent literature—we find that such a characteristics-sparse SDF cannot
adequately summarize the cross-section of expected stock returns. However, a relatively small
number of principal components of the universe of potential characteristics-based factors can
approximate the SDF quite well
%0 Generic
%1 kozak2017shrinking
%A Kozak, Serhiy
%A Nagel, Stefan
%A Santosh, Shrihari
%D 2017
%K factor-empirical-test sdf zoo-factor
%T Shrinking the Cross Section
%U https://papers.ssrn.com/sol3/papers.cfm?abstract_id=2945663
%X We construct a robust stochastic discount factor (SDF) that summarizes the joint explanatory
power of a large number of cross-sectional stock return predictors. Our method achieves robust
out-of-sample performance in this high-dimensional setting by imposing an economically
motivated prior on SDF coefficients that shrinks the contributions of low-variance principal
components of the candidate factors. While empirical asset pricing research has focused on SDFs
with a small number of characteristics-based factors—e.g., the four- or five-factor models
discussed in the recent literature—we find that such a characteristics-sparse SDF cannot
adequately summarize the cross-section of expected stock returns. However, a relatively small
number of principal components of the universe of potential characteristics-based factors can
approximate the SDF quite well
@preprint{kozak2017shrinking,
abstract = {We construct a robust stochastic discount factor (SDF) that summarizes the joint explanatory
power of a large number of cross-sectional stock return predictors. Our method achieves robust
out-of-sample performance in this high-dimensional setting by imposing an economically
motivated prior on SDF coefficients that shrinks the contributions of low-variance principal
components of the candidate factors. While empirical asset pricing research has focused on SDFs
with a small number of characteristics-based factors—e.g., the four- or five-factor models
discussed in the recent literature—we find that such a characteristics-sparse SDF cannot
adequately summarize the cross-section of expected stock returns. However, a relatively small
number of principal components of the universe of potential characteristics-based factors can
approximate the SDF quite well},
added-at = {2019-02-26T17:16:10.000+0100},
author = {Kozak, Serhiy and Nagel, Stefan and Santosh, Shrihari},
biburl = {https://www.bibsonomy.org/bibtex/22bd9297e7d225f7950acec3df6ac4727/antoinefalck},
interhash = {fba76cb06b2c130a685d3ae8e8cc00fa},
intrahash = {2bd9297e7d225f7950acec3df6ac4727},
keywords = {factor-empirical-test sdf zoo-factor},
timestamp = {2019-03-06T20:45:42.000+0100},
title = {Shrinking the Cross Section},
url = {https://papers.ssrn.com/sol3/papers.cfm?abstract_id=2945663},
year = 2017
}