Implements an MCMC algorithm to estimate a hierarchical multinomial logit model with a normal heterogeneity distribution. The algorithm uses a hybrid Gibbs Sampler with a random walk metropolis step for the MNL coefficients for each unit. Dependent variable may be discrete or continuous. Independent variables may be discrete or continuous with optional order constraints. Means of the distribution of heterogeneity can optionally be modeled as a linear function of unit characteristics variables.
| Version: | 1.1 |
| Depends: | R (≥ 2.10) |
| Suggests: | bayesm, MASS, lattice, Matrix |
| Published: | 2012-05-09 |
| Author: | Ryan Sermas, assisted by John V. Colias |
| Maintainer: | Ryan Sermas <DecisionAnalystR at decisionanalyst.com> |
| License: | GPL (≥ 3) |
| Copyright: | (C) 2012 Decision Analyst, Inc. (ChoiceModelR is a trademark of Decision Analyst, Inc.) |
| URL: | http://www.decisionanalyst.com |
| CRAN checks: | ChoiceModelR results |
| Package source: | ChoiceModelR_1.1.tar.gz |
| MacOS X binary: | ChoiceModelR_1.1.tgz |
| Windows binary: | ChoiceModelR_1.1.zip |
| Reference manual: | ChoiceModelR.pdf |
| Old sources: | ChoiceModelR archive |