Robust two-pass cross-sectional regressions: A minimum distance approach

Seung Ahn, Christopher Gadarowski, M. Fabricio Perez

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

We examine the asymptotic and finite-sample properties of the two-pass (TP) cross-sectional regressions estimators when factors and asset returns are conditionally heteroskedastic and/or autocorrelated. Using a minimum distance approach, we derive the heteroskedasticity- and/or autocorrelation-consistent (HAC) standard errors and the optimal TP estimator. A HAC model specification test statistic is also derived. Our Monte Carlo simulation results reveal the importance of controlling for autocorrelation. The HAC standard errors produce the most reliable inferences under autocorrelation. The HAC specification test is a viable alternative if the number of asset returns is small and the number of time-series observations is large.

Original languageEnglish (US)
Article numbernbs006
Pages (from-to)669-701
Number of pages33
JournalJournal of Financial Econometrics
Volume10
Issue number4
DOIs
StatePublished - Sep 2012

Fingerprint

Autocorrelation
Cross-sectional regression
Minimum distance
Heteroskedasticity
Estimator
Standard error
Asset returns
Specification test
Factors
Test statistic
Inference
Model specification
Monte Carlo simulation
Finite sample properties

Keywords

  • Cross-sectional regression
  • Factor model
  • Fama and MacBeth
  • Minimum distance
  • Robust standard errors
  • Two-pass

ASJC Scopus subject areas

  • Economics and Econometrics
  • Finance

Cite this

Robust two-pass cross-sectional regressions : A minimum distance approach. / Ahn, Seung; Gadarowski, Christopher; Fabricio Perez, M.

In: Journal of Financial Econometrics, Vol. 10, No. 4, nbs006, 09.2012, p. 669-701.

Research output: Contribution to journalArticle

Ahn, Seung ; Gadarowski, Christopher ; Fabricio Perez, M. / Robust two-pass cross-sectional regressions : A minimum distance approach. In: Journal of Financial Econometrics. 2012 ; Vol. 10, No. 4. pp. 669-701.
@article{239ff33168204b4fa3e851c7276bd7e7,
title = "Robust two-pass cross-sectional regressions: A minimum distance approach",
abstract = "We examine the asymptotic and finite-sample properties of the two-pass (TP) cross-sectional regressions estimators when factors and asset returns are conditionally heteroskedastic and/or autocorrelated. Using a minimum distance approach, we derive the heteroskedasticity- and/or autocorrelation-consistent (HAC) standard errors and the optimal TP estimator. A HAC model specification test statistic is also derived. Our Monte Carlo simulation results reveal the importance of controlling for autocorrelation. The HAC standard errors produce the most reliable inferences under autocorrelation. The HAC specification test is a viable alternative if the number of asset returns is small and the number of time-series observations is large.",
keywords = "Cross-sectional regression, Factor model, Fama and MacBeth, Minimum distance, Robust standard errors, Two-pass",
author = "Seung Ahn and Christopher Gadarowski and {Fabricio Perez}, M.",
year = "2012",
month = "9",
doi = "10.1093/jjfinec/nbs006",
language = "English (US)",
volume = "10",
pages = "669--701",
journal = "Journal of Financial Econometrics",
issn = "1479-8409",
publisher = "Oxford University Press",
number = "4",

}

TY - JOUR

T1 - Robust two-pass cross-sectional regressions

T2 - A minimum distance approach

AU - Ahn, Seung

AU - Gadarowski, Christopher

AU - Fabricio Perez, M.

PY - 2012/9

Y1 - 2012/9

N2 - We examine the asymptotic and finite-sample properties of the two-pass (TP) cross-sectional regressions estimators when factors and asset returns are conditionally heteroskedastic and/or autocorrelated. Using a minimum distance approach, we derive the heteroskedasticity- and/or autocorrelation-consistent (HAC) standard errors and the optimal TP estimator. A HAC model specification test statistic is also derived. Our Monte Carlo simulation results reveal the importance of controlling for autocorrelation. The HAC standard errors produce the most reliable inferences under autocorrelation. The HAC specification test is a viable alternative if the number of asset returns is small and the number of time-series observations is large.

AB - We examine the asymptotic and finite-sample properties of the two-pass (TP) cross-sectional regressions estimators when factors and asset returns are conditionally heteroskedastic and/or autocorrelated. Using a minimum distance approach, we derive the heteroskedasticity- and/or autocorrelation-consistent (HAC) standard errors and the optimal TP estimator. A HAC model specification test statistic is also derived. Our Monte Carlo simulation results reveal the importance of controlling for autocorrelation. The HAC standard errors produce the most reliable inferences under autocorrelation. The HAC specification test is a viable alternative if the number of asset returns is small and the number of time-series observations is large.

KW - Cross-sectional regression

KW - Factor model

KW - Fama and MacBeth

KW - Minimum distance

KW - Robust standard errors

KW - Two-pass

UR - http://www.scopus.com/inward/record.url?scp=84866373919&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84866373919&partnerID=8YFLogxK

U2 - 10.1093/jjfinec/nbs006

DO - 10.1093/jjfinec/nbs006

M3 - Article

AN - SCOPUS:84866373919

VL - 10

SP - 669

EP - 701

JO - Journal of Financial Econometrics

JF - Journal of Financial Econometrics

SN - 1479-8409

IS - 4

M1 - nbs006

ER -