A convenient method for the estimation of the multinomial logit model with fixed effects

Alessandro Iaria; Xavier D’Haultfœuille

doi:10.1016/j.econlet.2016.02.002

A convenient method for the estimation of the multinomial logit model with fixed effects

Alessandro Iaria, Xavier D’Haultfœuille

School of Economics

Research output: Contribution to journal › Article (Academic Journal) › peer-review

6 Citations (Scopus)

565 Downloads (Pure)

Abstract

The conditional maximum likelihood estimator of the fixed-effect logit model suffers from a curse of dimensionality that may have severely limited its use in practice. As the number of alternatives and the number of choice situations per individual increase, the number of addends in the denominator of the fixed-effect logit formula grows exponentially. We propose to by-pass this curse of dimensionality by exploiting a classic result by McFadden (1978) and to consistently estimate the fixed-effect logit model on random samples of permutations of the observed choice sequences.

Original language	English
Pages (from-to)	77-79
Number of pages	3
Journal	Economics Letters
Volume	141
Early online date	13 Feb 2016
DOIs	https://doi.org/10.1016/j.econlet.2016.02.002
Publication status	Published - Apr 2016

Keywords

Sampling of alternatives; Restricted choice sets; Multinomial fixed effect logit; Conditional logit; Panel data logit

Access to Document

10.1016/j.econlet.2016.02.002

Full-text PDF (accepted author manuscript)
This is the accepted author manuscript (AAM). The final published version (version of record) is available online via Elsevier at https://doi.org/10.1016/j.econlet.2016.02.002 . Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 445 KBLicence: CC BY-NC-ND

Handle.net

Persistent link

Dr Alessandro Iaria
- alessandro.iariabristol.acuk
- School of Economics - Senior Lecturer in Economics
Person: Academic

Cite this

@article{5e20258ed35d455f8aa9aef756ad4ea9,

title = "A convenient method for the estimation of the multinomial logit model with fixed effects",

abstract = "The conditional maximum likelihood estimator of the fixed-effect logit model suffers from a curse of dimensionality that may have severely limited its use in practice. As the number of alternatives and the number of choice situations per individual increase, the number of addends in the denominator of the fixed-effect logit formula grows exponentially. We propose to by-pass this curse of dimensionality by exploiting a classic result by McFadden (1978) and to consistently estimate the fixed-effect logit model on random samples of permutations of the observed choice sequences.",

keywords = "Sampling of alternatives; Restricted choice sets; Multinomial fixed effect logit; Conditional logit; Panel data logit",

author = "Alessandro Iaria and Xavier D{\textquoteright}Haultf{\oe}uille",

year = "2016",

month = apr,

doi = "10.1016/j.econlet.2016.02.002",

language = "English",

volume = "141",

pages = "77--79",

journal = "Economics Letters",

issn = "0165-1765",

publisher = "Amsterdam:Elsevier",

}

TY - JOUR

T1 - A convenient method for the estimation of the multinomial logit model with fixed effects

AU - Iaria, Alessandro

AU - D’Haultfœuille, Xavier

PY - 2016/4

Y1 - 2016/4

N2 - The conditional maximum likelihood estimator of the fixed-effect logit model suffers from a curse of dimensionality that may have severely limited its use in practice. As the number of alternatives and the number of choice situations per individual increase, the number of addends in the denominator of the fixed-effect logit formula grows exponentially. We propose to by-pass this curse of dimensionality by exploiting a classic result by McFadden (1978) and to consistently estimate the fixed-effect logit model on random samples of permutations of the observed choice sequences.

AB - The conditional maximum likelihood estimator of the fixed-effect logit model suffers from a curse of dimensionality that may have severely limited its use in practice. As the number of alternatives and the number of choice situations per individual increase, the number of addends in the denominator of the fixed-effect logit formula grows exponentially. We propose to by-pass this curse of dimensionality by exploiting a classic result by McFadden (1978) and to consistently estimate the fixed-effect logit model on random samples of permutations of the observed choice sequences.

KW - Sampling of alternatives; Restricted choice sets; Multinomial fixed effect logit; Conditional logit; Panel data logit

U2 - 10.1016/j.econlet.2016.02.002

DO - 10.1016/j.econlet.2016.02.002

M3 - Article (Academic Journal)

SN - 0165-1765

VL - 141

SP - 77

EP - 79

JO - Economics Letters

JF - Economics Letters

ER -

A convenient method for the estimation of the multinomial logit model with fixed effects

Abstract

Keywords

Access to Document

Handle.net

Fingerprint

Profiles

Dr Alessandro Iaria

Cite this