Using Principal Component Analysis to Estimate a High Dimensional Factor Model with High-Frequency Data

43 Pages Posted: 7 Oct 2015 Last revised: 11 Oct 2016

See all articles by Yacine Ait-Sahalia

Yacine Ait-Sahalia

Princeton University - Department of Economics

Dacheng Xiu

University of Chicago - Booth School of Business

Date Written: October 7, 2016

Abstract

This paper constructs an estimator for the number of common factors in a setting where both the sampling frequency and the number of variables increase. Empirically, we document that the covariance matrix of a large portfolio of US equities is well represented by a low rank common structure with sparse residual matrix. When employed for out-of-sample portfolio allocation, the proposed estimator largely outperforms the sample covariance estimator.

Keywords: High-dimensional data, high-frequency, latent factor model, principal components, portfolio optimization

JEL Classification: C13, C14, C55, C58, G01

Suggested Citation

Ait-Sahalia, Yacine and Xiu, Dacheng, Using Principal Component Analysis to Estimate a High Dimensional Factor Model with High-Frequency Data (October 7, 2016). Chicago Booth Research Paper No. 15-43, Available at SSRN: https://ssrn.com/abstract=2669506 or http://dx.doi.org/10.2139/ssrn.2669506

Yacine Ait-Sahalia

Princeton University - Department of Economics ( email )

Fisher Hall
Princeton, NJ 08544
United States
609-258-4015 (Phone)
609-258-5398 (Fax)

Dacheng Xiu (Contact Author)

University of Chicago - Booth School of Business ( email )

5807 S. Woodlawn Avenue
Chicago, IL 60637
United States

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
899
Abstract Views
3,151
Rank
48,807
PlumX Metrics