A Dimensionality-Robust Test in Multiple Predictive Regression

43 Pages Posted: 6 Oct 2019 Last revised: 3 Feb 2020

See all articles by Ke-Li Xu

Ke-Li Xu

Indiana University Bloomington; Texas A&M University

Junjie Guo

Indiana University Bloomington, Department of Economics

Date Written: July 16, 2019


We consider inference of predictive regression with multiple predictors. Extant tests for predictability, including those constructed with robustness to unknown persistence and endogeneity of predictors, may perform unsatisfactorily and tend to discover spurious predictability as the number of predictors increases. We propose a battery of new instrumental-variables based tests which involve enforcement or partial enforcement of the null hypothesis in variance estimation and analyze their asymptotic properties. A test based on the parsimonious system approach is recommended. Empirical Monte Carlos demonstrate the remarkable finite-sample performance regardless of numerosity of predictors. Empirical application to equity premium predictability is also provided.

Keywords: curse of dimensionality; Lagrange-multipliers test; persistence; predictive regression; return predictability

JEL Classification: C32; C53; C58; G12

Suggested Citation

Xu, Ke-Li and Guo, Junjie, A Dimensionality-Robust Test in Multiple Predictive Regression (July 16, 2019). Available at SSRN: https://ssrn.com/abstract=3458074 or http://dx.doi.org/10.2139/ssrn.3458074

Ke-Li Xu (Contact Author)

Indiana University Bloomington ( email )

100 S. Woodlawn Ave.
Department of Economics, Wylie Hall
Bloomington, IN 47405-7104
United States

HOME PAGE: http://sites.google.com/site/xukeli2015/

Texas A&M University ( email )

3063 Allen, 4228 TAMU
Department of Economics, TAMU
College Station, TX 77843-4228
United States

HOME PAGE: http://econweb.tamu.edu/keli/

Junjie Guo

Indiana University Bloomington, Department of Economics ( email )

Bloomington, IN
United States

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

Paper statistics

Abstract Views
PlumX Metrics