Standard and Shuffled Halton Sequences in a Mixed Logit Model

Modeling consumer choice in different areas has lead to an increase use of discrete choice models. Probit or Multinomial Logit Models are often the base of further empirical research of consumer choice. In some of these models the equations to solve have no closed-form expression. They include multi-dimensional integrals which can not be solved analytically. Simulation methods have been developed to approximate a solution for these integrals. This paper describes the Standard Halton sequence and a modification of it, the Shuffled Halton sequence. Both are simulation methods which can reduce computational effort compared to a random sequence. We compare the simulation methods in their coverage of the multi-dimensional area and in their estimation results using data of consumer choice on grocery store formats.


Issue Date:
2008-09
Publication Type:
Working or Discussion Paper
DOI and Other Identifiers:
ISSN 1615-0473 (Other)
PURL Identifier:
http://purl.umn.edu/93856
Page range:
6-27
Total Pages:
34
JEL Codes:
C15; C25
Series Statement:
Hohenheimer Agrarökonomische Arbeitsberichte
17




 Record created 2017-04-01, last modified 2017-08-25

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)