Latest News

Announcing Discrete Choice Analysis Tools v2.0 for GAUSS


The new discrete choice analysis tools offers econometricians, micro-economists, public choice researchers, survey data analysts, sociologists, epidemiologists, and accident analysts (insurance and safety analysts) the following tools:

  • A better handling of large data sets
  • A full set of built-in tools to accommodate individual model specificity
    • Adjust parameter bounds
    • Choose between linear and nonlinear constraints
    • Change starting values
    • Specify Gradient and Hessian procedures
  • New logistic regression modelling for large scale classification
  • New data and parameter input procedures which make model set-up and implementation more intuitive
  • Options to export output in publication quality formatted tables

The Discrete Choice Analysis tools (2.0) offers new features in three areas: supported models, output and reporting.

Supported Models:

  • Large Scale Data Classification: 
    • Large-scale binary linear classification using support vector machines [SVM] or logistic regression [LR] methodology
    • Cross-validation of model parameters and prediction plotting
    • Easy access output includes estimated prediction weights, predicted classifications and cross-validation accuracy
  • Adjacent Categories Multinomial Logit Model
  • Logit and Probit Regression Models
    • Handles normal or extreme value distributions
  • Conditional Logit Models
    • Includes both variables that are attributes of the responses as well as, optionally, exogenous variables that are properties of cases
  • Mutltinomial Logit Model
  • Negative Binomial Regression Model
    • A zero-inflated negative binomial model can be estimated where the probability of the zero category is a mixture of a negative binomial consistent probability and an excess probability. The mixture coefficient can be a function of independent variables.
  • Nested Logit Regression Model
  • Ordered Logit and Probit Regression Models
  • Possion Regression Model
  • Stereotype Multinomial Logit Model Outputs: GAUSS Easy to access, store, and export:


  • Predicted counts and residuals
  • Parameter estimates
  • Variance-covariance matrix for coefficient estimates
  • Percentages of dependent variables by category (where applicable)
  • Complete data description of all independent variables
  • Marginal effects of independent variables (by category of dependent variable, when applicable)
  • Variance-covariance matrices of marginal effects


  • Full model and restricted model log-likelihoods
  • Chi-square statistic
  • Agresti’s G-squared statistic
  • Likelihood ratio statistics and accompanying probability values
  • McFadden’s Psuedo R-squared
  • McKelvey and Zovcina’s Psuedo R-Squared
  • Cragg and Uhler’s normed likelihood ratios
  • Count R-Squared
  • Adjusted count R-Squared
  • Akaike and Bayesian information criterions

For examples on adjacent categories logit model click here (external link), on binary logit model click here (external link) and logistic regression model click here (external link)