High-Dimensional Predictive Regression in the Presence of Cointegration

46 Pages Posted: 15 Oct 2016 Last revised: 1 Mar 2019

See all articles by Bonsoo Koo

Bonsoo Koo

Monash Business School

Heather M. Anderson

Monash University - Department of Econometrics and Business Statistics; Department of Econometrics and Business Statistics

Myung Hwan Seo

Seoul National University - School of Economics

Wenying Yao

University of Melbourne - Melbourne Business School

Date Written: October 12, 2016

Abstract

While a great number of predictive variables for stock returns have been suggested, their prediction power is unstable. We propose a Least Absolute Shrinkage and Selection Operator (LASSO) estimator of a predictive regression in which stock returns are conditioned on a large set of lagged covariates, some of which are highly persistent and potentially cointegrated. We establish the asymptotic properties of the proposed LASSO estimator and validate our theoretical findings using simulation studies. The application of this proposed LASSO approach to forecasting stock returns suggests that cointegrating relationships among the persistent predictors leads to a significant improvement in the prediction of stock returns over various competing models in the mean squared error sense.

Keywords: return predictability, predictive regression, cointegration, LASSO

JEL Classification: C13, C22, G12, G17

Suggested Citation

Koo, Bonsoo and Anderson, Heather and Seo, Myung Hwan and Yao, Wenying, High-Dimensional Predictive Regression in the Presence of Cointegration (October 12, 2016). Available at SSRN: https://ssrn.com/abstract=2851677 or http://dx.doi.org/10.2139/ssrn.2851677

Bonsoo Koo

Monash Business School ( email )

Wellington Road
Clayton, Victoria 3168
Australia
+61 3 9905 0547 (Phone)
+61 3 9905 5474 (Fax)

Heather Anderson

Monash University - Department of Econometrics and Business Statistics ( email )

900 Dandenong Rd
Caulfield, Victoria 3145
Australia

Department of Econometrics and Business Statistics ( email )

900 Dandenong Road
Caulfield East, 3145
Australia

Myung Hwan Seo (Contact Author)

Seoul National University - School of Economics ( email )

San 56-1, Silim-dong, Kwanak-ku
Seoul 151-742

Wenying Yao

University of Melbourne - Melbourne Business School ( email )

200 Leicester Street
Carlton, Victoria 3053 3186
Australia

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
379
Abstract Views
1,857
rank
116,068
PlumX Metrics