Likelihood corrections for two-way models

Koen Jochmans, Taisuke Otsu

Research output: Contribution to journalArticle

Abstract

The use of panel data models with two-way fixed effects is widespread. Incidental-parameter bias, however, invalidates inference based on the (profile) likelihood. We consider modifications to the likelihood that yield asymptotically-unbiased estimators as well as test statistics that are size correct under rectangular-array asymptotics. The modifications are widely applicable and easy to implement. Through several examples we illustrate that the modifications can lead to dramatic improvements relative to maximum likelihood, both in terms of point estimation and inference.

Original languageEnglish
Pages (from-to)227-242
Number of pages16
JournalAnnals of Economics and Statistics
Issue number134
DOIs
Publication statusPublished - 2019 Jan 1
Externally publishedYes

Fingerprint

Likelihood
Profile Likelihood
Point Estimation
Fixed Effects
Unbiased estimator
Panel Data
Data Model
Test Statistic
Maximum Likelihood
statistics
Model
trend
Inference
Estimator
Fixed effects
Test statistic
Maximum likelihood

Keywords

  • Fixed Effects
  • Information Bias
  • Modified Profile Likelihood
  • Panel Data
  • Penalization
  • Rectangular-Array Asymptotics

ASJC Scopus subject areas

  • Statistics and Probability
  • Social Sciences (miscellaneous)
  • Economics and Econometrics
  • Statistics, Probability and Uncertainty

Cite this

Likelihood corrections for two-way models. / Jochmans, Koen; Otsu, Taisuke.

In: Annals of Economics and Statistics, No. 134, 01.01.2019, p. 227-242.

Research output: Contribution to journalArticle

@article{bb7fd2e21bac4e5f957e19306d66cee2,
title = "Likelihood corrections for two-way models",
abstract = "The use of panel data models with two-way fixed effects is widespread. Incidental-parameter bias, however, invalidates inference based on the (profile) likelihood. We consider modifications to the likelihood that yield asymptotically-unbiased estimators as well as test statistics that are size correct under rectangular-array asymptotics. The modifications are widely applicable and easy to implement. Through several examples we illustrate that the modifications can lead to dramatic improvements relative to maximum likelihood, both in terms of point estimation and inference.",
keywords = "Fixed Effects, Information Bias, Modified Profile Likelihood, Panel Data, Penalization, Rectangular-Array Asymptotics",
author = "Koen Jochmans and Taisuke Otsu",
year = "2019",
month = "1",
day = "1",
doi = "10.15609/annaeconstat2009.134.0227",
language = "English",
pages = "227--242",
journal = "Annals of Economics and Statistics",
issn = "2115-4430",
publisher = "Groupe des ecoles nationales d'economie et statistique",
number = "134",

}

TY - JOUR

T1 - Likelihood corrections for two-way models

AU - Jochmans, Koen

AU - Otsu, Taisuke

PY - 2019/1/1

Y1 - 2019/1/1

N2 - The use of panel data models with two-way fixed effects is widespread. Incidental-parameter bias, however, invalidates inference based on the (profile) likelihood. We consider modifications to the likelihood that yield asymptotically-unbiased estimators as well as test statistics that are size correct under rectangular-array asymptotics. The modifications are widely applicable and easy to implement. Through several examples we illustrate that the modifications can lead to dramatic improvements relative to maximum likelihood, both in terms of point estimation and inference.

AB - The use of panel data models with two-way fixed effects is widespread. Incidental-parameter bias, however, invalidates inference based on the (profile) likelihood. We consider modifications to the likelihood that yield asymptotically-unbiased estimators as well as test statistics that are size correct under rectangular-array asymptotics. The modifications are widely applicable and easy to implement. Through several examples we illustrate that the modifications can lead to dramatic improvements relative to maximum likelihood, both in terms of point estimation and inference.

KW - Fixed Effects

KW - Information Bias

KW - Modified Profile Likelihood

KW - Panel Data

KW - Penalization

KW - Rectangular-Array Asymptotics

UR - http://www.scopus.com/inward/record.url?scp=85069711324&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069711324&partnerID=8YFLogxK

U2 - 10.15609/annaeconstat2009.134.0227

DO - 10.15609/annaeconstat2009.134.0227

M3 - Article

AN - SCOPUS:85069711324

SP - 227

EP - 242

JO - Annals of Economics and Statistics

JF - Annals of Economics and Statistics

SN - 2115-4430

IS - 134

ER -