Statistical Innovations logo
Latent GOLD® magnifying glass  New release: Latent GOLD® 3.0 >> 






  Latent GOLD®   go to section and expand

  Latent GOLD® Choice  go to section and expand
Order
Download Demo
Documentation
Tutorials
FAQ
Articles

  GOLDMineR®  go to section and expand
  SI-CHAID®  >





  Latent GOLD® Choice: About Latent GOLD Choice Analysis.

Types of Models

Latent GOLD® Choice, available as a stand-alone program or as an optional add-on module for Latent GOLD 4.0, supports the following kinds of latent class choice models:
  • First choice models - an extended multinomial logit model (MNL) is used to estimate the probability of making a specific choice among a set of alternatives as a function of choice attributes and individual characteristics (predictors).
  • Ranking models - The sequential logit model is used for situations where a 1st and 2nd choice, 1st and last choice (best-worst, max-diff), more than 2 choices (pick k out of K, pick any out of K), or a complete ranking of all alternatives. Respondent cases may contain different numbers of choice sets.
  • Allocation models - Replication weights may be used with first choice and ranking models to handle designs where respondents allocate a number of votes (purchases, points) among the various choice alternatives.
  • Ratings models - Traditional conjoint rating models can also be estimated.
Latent class (LC) choice models account for heterogeneity in the data by allowing for the fact that different population segments (latent classes) express different preferences in making their choices. A variety of various model fit statistics are computed. Covariates may also be included in the model for improved description/ prediction of the segments.

Types of Applications

LC choice models are appropriate for both Stated Preference (SP) as well as Revealed Preference (RP) data. SP data is generally obtained from choice survey experiments. Common SP applications are the identification of market segments and the evaluation of market potential and estimation of market share for new products or services for each segment. Choice attributes may include brand and price in which case the resulting model allows for simulation of market shares under various pricing scenarios. Covariates may be included in a model to predict segment membership and choices for cases not included in the survey.

To place your order, fill out our online order form or call: (617) 489-4490.

Download a Free Demo!


E-mail Contact: robert@statisticalinnovations.com
Address: Statistical Innovations, 375 Concord Avenue, Belmont, MA 02478-3084
Phone: +1.617.489.4490
Fax: +1.617.489.4499