First difference maximum likelihood and dynamic panel estimation
First difference maximum likelihood (FDML) seems an attractive estimation methodology in dynamic panel data modeling because differencing eliminates fixed effects and, in the case of a unit root, differencing transforms the data to stationarity, thereby addressing both incidental parameter problems...
Saved in:
Main Authors: | , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2013
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/soe_research/2173 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.soe_research-3173 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.soe_research-31732018-05-25T06:54:13Z First difference maximum likelihood and dynamic panel estimation HAN, Chirok PHILLIPS, Peter C. B. First difference maximum likelihood (FDML) seems an attractive estimation methodology in dynamic panel data modeling because differencing eliminates fixed effects and, in the case of a unit root, differencing transforms the data to stationarity, thereby addressing both incidental parameter problems and the possible effects of nonstationarity. This paper draws attention to certain pathologies that arise in the use of FDML that have gone unnoticed in the literature and that affect both finite sample performance and asymptotics. FDML uses the Gaussian likelihood function for first differenced data and parameter estimation is based on the whole domain over which the log-likelihood is defined. However, extending the domain of the likelihood beyond the stationary region has certain consequences that have a major effect on finite sample and asymptotic performance. First, the extended likelihood is not the true likelihood even in the Gaussian case and it has a finite upper bound of definition. Second, it is often bimodal, and one of its peaks can be so peculiar that numerical maximization of the extended likelihood frequently fails to locate the global maximum. As a result of these pathologies, the FDML estimator is a restricted estimator, numerical implementation is not straightforward and asymptotics are hard to derive in cases where the peculiarity occurs with non-negligible probabilities. The peculiarities in the likelihood are found to be particularly marked in time series with a unit root. In this case, the asymptotic distribution of the FDMLE has bounded support and its density is infinite at the upper bound when the time series sample size T --> infinity. As the panel width n --> infinity the pathology is removed and the limit theory is normal. This result applies even for T fixed and we present an expression for the asymptotic distribution which does not depend on the time dimension. We also show how this limit theory depends on the form of the extended likelihood. (C) 2013 Elsevier B.V. All rights reserved. 2013-01-07T08:00:00Z text https://ink.library.smu.edu.sg/soe_research/2173 info:doi/10.1016/j.jeconom.2013.03.003 Research Collection School Of Economics eng Institutional Knowledge at Singapore Management University Asymptote Bounded support Dynamic panel Efficiency First difference MLE Likelihood Quartic equation Restricted extremum estimator Econometrics |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Asymptote Bounded support Dynamic panel Efficiency First difference MLE Likelihood Quartic equation Restricted extremum estimator Econometrics |
spellingShingle |
Asymptote Bounded support Dynamic panel Efficiency First difference MLE Likelihood Quartic equation Restricted extremum estimator Econometrics HAN, Chirok PHILLIPS, Peter C. B. First difference maximum likelihood and dynamic panel estimation |
description |
First difference maximum likelihood (FDML) seems an attractive estimation methodology in dynamic panel data modeling because differencing eliminates fixed effects and, in the case of a unit root, differencing transforms the data to stationarity, thereby addressing both incidental parameter problems and the possible effects of nonstationarity. This paper draws attention to certain pathologies that arise in the use of FDML that have gone unnoticed in the literature and that affect both finite sample performance and asymptotics. FDML uses the Gaussian likelihood function for first differenced data and parameter estimation is based on the whole domain over which the log-likelihood is defined. However, extending the domain of the likelihood beyond the stationary region has certain consequences that have a major effect on finite sample and asymptotic performance. First, the extended likelihood is not the true likelihood even in the Gaussian case and it has a finite upper bound of definition. Second, it is often bimodal, and one of its peaks can be so peculiar that numerical maximization of the extended likelihood frequently fails to locate the global maximum. As a result of these pathologies, the FDML estimator is a restricted estimator, numerical implementation is not straightforward and asymptotics are hard to derive in cases where the peculiarity occurs with non-negligible probabilities. The peculiarities in the likelihood are found to be particularly marked in time series with a unit root. In this case, the asymptotic distribution of the FDMLE has bounded support and its density is infinite at the upper bound when the time series sample size T --> infinity. As the panel width n --> infinity the pathology is removed and the limit theory is normal. This result applies even for T fixed and we present an expression for the asymptotic distribution which does not depend on the time dimension. We also show how this limit theory depends on the form of the extended likelihood. (C) 2013 Elsevier B.V. All rights reserved. |
format |
text |
author |
HAN, Chirok PHILLIPS, Peter C. B. |
author_facet |
HAN, Chirok PHILLIPS, Peter C. B. |
author_sort |
HAN, Chirok |
title |
First difference maximum likelihood and dynamic panel estimation |
title_short |
First difference maximum likelihood and dynamic panel estimation |
title_full |
First difference maximum likelihood and dynamic panel estimation |
title_fullStr |
First difference maximum likelihood and dynamic panel estimation |
title_full_unstemmed |
First difference maximum likelihood and dynamic panel estimation |
title_sort |
first difference maximum likelihood and dynamic panel estimation |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2013 |
url |
https://ink.library.smu.edu.sg/soe_research/2173 |
_version_ |
1770574125275807744 |