On the Estimation and Testing of Predictive Panel Regressions

Hande Karabiyik; Joakim Westerlund; Paresh Kumar Narayan

doi:10.1016/j.intfin.2016.07.003

On the Estimation and Testing of Predictive Panel Regressions

Hande Karabiyik, Joakim Westerlund, Paresh Kumar Narayan

Department of Economics

Deakin University

Research output: Contribution to journal › Article › peer-review

Abstract

Hjalmarsson (2010) considers an OLS-based estimator of predictive panel regressions that is argued to be mixed normal under very general conditions. In a recent paper, Westerlund et al. (2016) show that while consistent, the estimator is generally not mixed normal, which invalidates standard normal and chi-squared inference. The purpose of the present paper is to study the consequences of this theoretical result in small samples, which is done using both simulated and real data.

Original language	English
Pages (from-to)	115–125
Number of pages	11
Journal	Journal of International Financial Markets, Institutions, and Money
Volume	45
DOIs	https://doi.org/10.1016/j.intfin.2016.07.003
Publication status	Published - 2016

Subject classification (UKÄ)

Economics

Free keywords

Common factors
Mixed normality
Panel data
Predictive regression

Access to Document

10.1016/j.intfin.2016.07.003

Cite this

@article{6cc5b44b4e884f6a80734d2c794808c7,

title = "On the Estimation and Testing of Predictive Panel Regressions",

abstract = "Hjalmarsson (2010) considers an OLS-based estimator of predictive panel regressions that is argued to be mixed normal under very general conditions. In a recent paper, Westerlund et al. (2016) show that while consistent, the estimator is generally not mixed normal, which invalidates standard normal and chi-squared inference. The purpose of the present paper is to study the consequences of this theoretical result in small samples, which is done using both simulated and real data.",

keywords = "Common factors, Mixed normality, Panel data, Predictive regression",

author = "Hande Karabiyik and Joakim Westerlund and Narayan, {Paresh Kumar}",

year = "2016",

doi = "10.1016/j.intfin.2016.07.003",

language = "English",

volume = "45",

pages = "115–125",

journal = "Journal of International Financial Markets, Institutions, and Money",

issn = "1042-4431",

publisher = "North-Holland",

}

TY - JOUR

T1 - On the Estimation and Testing of Predictive Panel Regressions

AU - Karabiyik, Hande

AU - Westerlund, Joakim

AU - Narayan, Paresh Kumar

PY - 2016

Y1 - 2016

N2 - Hjalmarsson (2010) considers an OLS-based estimator of predictive panel regressions that is argued to be mixed normal under very general conditions. In a recent paper, Westerlund et al. (2016) show that while consistent, the estimator is generally not mixed normal, which invalidates standard normal and chi-squared inference. The purpose of the present paper is to study the consequences of this theoretical result in small samples, which is done using both simulated and real data.

AB - Hjalmarsson (2010) considers an OLS-based estimator of predictive panel regressions that is argued to be mixed normal under very general conditions. In a recent paper, Westerlund et al. (2016) show that while consistent, the estimator is generally not mixed normal, which invalidates standard normal and chi-squared inference. The purpose of the present paper is to study the consequences of this theoretical result in small samples, which is done using both simulated and real data.

KW - Common factors

KW - Mixed normality

KW - Panel data

KW - Predictive regression

UR - http://www.scopus.com/inward/record.url?scp=84981731676&partnerID=8YFLogxK

U2 - 10.1016/j.intfin.2016.07.003

DO - 10.1016/j.intfin.2016.07.003

M3 - Article

SN - 1042-4431

VL - 45

SP - 115

EP - 125

JO - Journal of International Financial Markets, Institutions, and Money

JF - Journal of International Financial Markets, Institutions, and Money

ER -

On the Estimation and Testing of Predictive Panel Regressions

Abstract

Subject classification (UKÄ)

Free keywords

Access to Document

Other files and links

Fingerprint

Cite this