Implements a class of context-dependent discrete choice models,
including the standard random utility maximization (RUM) model, classical
and generalized random regret minimization (RRM) models, the random
advantage maximization (RAM) model, as well as the Emergent Value (EV)
model and the contextual random utility maximization (CRUM) model, which
explicitly incorporate measures of context dependence. In addition,
pairwise normalization (PN) and range normalization (RN) models are
supported. Both fixed-parameter and random-parameter specifications can
be estimated, the latter allowing for preference heterogeneity. All models are
formulated within a logit framework under the assumption of independently
and identically distributed (i.i.d.) Gumbel error terms. The implemented
methods are based on Tversky and Simonson (1993)