Panel conditional and multinomial logit with time-varying parameters

Research output: Contribution to journalArticle

Abstract

Panel conditional logit estimators (PCLE) in the literature use mostly time-constant parameters. If the panel periods are volatile or long, however, the model parameters can change much. Hence this paper generalizes PCLE with time-constant parameters to PCLE with time-varying parameters; both static and dynamic PCLE are considered for this. The main finding is that time-varying parameters are fully allowed for static PCLE and the dynamic "pseudo" PCLE of [Bartolucci, F. and V. Nigro. 2010. "A Dynamic Model for Binary Panel Data with Unobserved Heterogeneity Admitting a n $ n$-Consistent Conditional Estimator." Econometrica 78: 719-733] that are thus recommended to practitioners. As a further generalization, static "panel conditional multinomial logit estimator (PML)" with time-varying parameters is also examined. As it turns out, time-varying parameters are also fully allowed for PML. With no error term serial correlation allowed in PCLE and dynamic PCLE's being restrictive in their assumptions, time-varying parameters provide an alternative avenue to inject dynamics and flexibility into PCLE and PML. Since PCLE and PML converge straightforwardly in computation, allowing time-varying parameters in PCLE and PML is "computationally free." A simulation study is also provided.

Original languageEnglish
Pages (from-to)317-337
Number of pages21
JournalStudies in Nonlinear Dynamics and Econometrics
Volume19
Issue number3
DOIs
Publication statusPublished - 2015 Jun 1

Fingerprint

Multinomial Logit
Time-varying Parameters
Logit
Estimator
Time Constant
Time-varying parameters
Multinomial logit
Conditional logit
time
Unobserved Heterogeneity
Serial Correlation
Binary Data
Volatiles
Panel Data
flexibility
Error term

Keywords

  • binary choice
  • conditional logit
  • multinomial choice
  • panel data
  • time-varying parameters

ASJC Scopus subject areas

  • Economics and Econometrics
  • Social Sciences (miscellaneous)
  • Analysis

Cite this

Panel conditional and multinomial logit with time-varying parameters. / Lee, Myoung-jae.

In: Studies in Nonlinear Dynamics and Econometrics, Vol. 19, No. 3, 01.06.2015, p. 317-337.

Research output: Contribution to journalArticle

@article{e3349ffe910b4ee39ef2ae89a01d5bd2,
title = "Panel conditional and multinomial logit with time-varying parameters",
abstract = "Panel conditional logit estimators (PCLE) in the literature use mostly time-constant parameters. If the panel periods are volatile or long, however, the model parameters can change much. Hence this paper generalizes PCLE with time-constant parameters to PCLE with time-varying parameters; both static and dynamic PCLE are considered for this. The main finding is that time-varying parameters are fully allowed for static PCLE and the dynamic {"}pseudo{"} PCLE of [Bartolucci, F. and V. Nigro. 2010. {"}A Dynamic Model for Binary Panel Data with Unobserved Heterogeneity Admitting a n $ n$-Consistent Conditional Estimator.{"} Econometrica 78: 719-733] that are thus recommended to practitioners. As a further generalization, static {"}panel conditional multinomial logit estimator (PML){"} with time-varying parameters is also examined. As it turns out, time-varying parameters are also fully allowed for PML. With no error term serial correlation allowed in PCLE and dynamic PCLE's being restrictive in their assumptions, time-varying parameters provide an alternative avenue to inject dynamics and flexibility into PCLE and PML. Since PCLE and PML converge straightforwardly in computation, allowing time-varying parameters in PCLE and PML is {"}computationally free.{"} A simulation study is also provided.",
keywords = "binary choice, conditional logit, multinomial choice, panel data, time-varying parameters",
author = "Myoung-jae Lee",
year = "2015",
month = "6",
day = "1",
doi = "10.1515/snde-2014-0003",
language = "English",
volume = "19",
pages = "317--337",
journal = "Studies in Nonlinear Dynamics and Econometrics",
issn = "1081-1826",
publisher = "Berkeley Electronic Press",
number = "3",

}

TY - JOUR

T1 - Panel conditional and multinomial logit with time-varying parameters

AU - Lee, Myoung-jae

PY - 2015/6/1

Y1 - 2015/6/1

N2 - Panel conditional logit estimators (PCLE) in the literature use mostly time-constant parameters. If the panel periods are volatile or long, however, the model parameters can change much. Hence this paper generalizes PCLE with time-constant parameters to PCLE with time-varying parameters; both static and dynamic PCLE are considered for this. The main finding is that time-varying parameters are fully allowed for static PCLE and the dynamic "pseudo" PCLE of [Bartolucci, F. and V. Nigro. 2010. "A Dynamic Model for Binary Panel Data with Unobserved Heterogeneity Admitting a n $ n$-Consistent Conditional Estimator." Econometrica 78: 719-733] that are thus recommended to practitioners. As a further generalization, static "panel conditional multinomial logit estimator (PML)" with time-varying parameters is also examined. As it turns out, time-varying parameters are also fully allowed for PML. With no error term serial correlation allowed in PCLE and dynamic PCLE's being restrictive in their assumptions, time-varying parameters provide an alternative avenue to inject dynamics and flexibility into PCLE and PML. Since PCLE and PML converge straightforwardly in computation, allowing time-varying parameters in PCLE and PML is "computationally free." A simulation study is also provided.

AB - Panel conditional logit estimators (PCLE) in the literature use mostly time-constant parameters. If the panel periods are volatile or long, however, the model parameters can change much. Hence this paper generalizes PCLE with time-constant parameters to PCLE with time-varying parameters; both static and dynamic PCLE are considered for this. The main finding is that time-varying parameters are fully allowed for static PCLE and the dynamic "pseudo" PCLE of [Bartolucci, F. and V. Nigro. 2010. "A Dynamic Model for Binary Panel Data with Unobserved Heterogeneity Admitting a n $ n$-Consistent Conditional Estimator." Econometrica 78: 719-733] that are thus recommended to practitioners. As a further generalization, static "panel conditional multinomial logit estimator (PML)" with time-varying parameters is also examined. As it turns out, time-varying parameters are also fully allowed for PML. With no error term serial correlation allowed in PCLE and dynamic PCLE's being restrictive in their assumptions, time-varying parameters provide an alternative avenue to inject dynamics and flexibility into PCLE and PML. Since PCLE and PML converge straightforwardly in computation, allowing time-varying parameters in PCLE and PML is "computationally free." A simulation study is also provided.

KW - binary choice

KW - conditional logit

KW - multinomial choice

KW - panel data

KW - time-varying parameters

UR - http://www.scopus.com/inward/record.url?scp=84930026747&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84930026747&partnerID=8YFLogxK

U2 - 10.1515/snde-2014-0003

DO - 10.1515/snde-2014-0003

M3 - Article

AN - SCOPUS:84930026747

VL - 19

SP - 317

EP - 337

JO - Studies in Nonlinear Dynamics and Econometrics

JF - Studies in Nonlinear Dynamics and Econometrics

SN - 1081-1826

IS - 3

ER -