MM ALGORITHM FOR GENERAL MIXED MULTINOMIAL LOGIT MODELS

This paper develops a new technique for estimating mixed logit models with a simple minorization–maximization (MM) algorithm. The algorithm requires minimal coding and is easy to implement for a variety of mixed logit models. Most importantly, the algorithm has a very low cost per iteration relative...

Full description

Saved in:
Bibliographic Details
Published inJournal of applied econometrics (Chichester, England) Vol. 32; no. 4; pp. 841 - 857
Main Author JAMES, JONATHAN
Format Journal Article
LanguageEnglish
Published Chichester Wiley (Variant) 01.06.2017
Wiley-Blackwell
Wiley Periodicals Inc
Subjects
Algorithms
Asymptotic methods
Asymptotic properties
Coding
Econometrics
Estimation
Iterative methods
Logit models
Low cost
Mathematical models
Maximization
Production methods
Savings
Welfare reform
Online AccessGet full text
ISSN0883-7252
1099-1255
DOI10.1002/jae.2532

Cover

More Information
Summary:This paper develops a new technique for estimating mixed logit models with a simple minorization–maximization (MM) algorithm. The algorithm requires minimal coding and is easy to implement for a variety of mixed logit models. Most importantly, the algorithm has a very low cost per iteration relative to current methods, producing substantial computational savings. In addition, the method is asymptotically consistent, efficient and globally convergent.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0883-7252
1099-1255
DOI:10.1002/jae.2532