prepare_mnp_data: Prepare inputs for Bayesian multinomial probit estimation

In choicer: Discrete Choice Models for Economic Applications

Prepare inputs for Bayesian multinomial probit estimation

Description

Prepares and validates inputs for Bayesian multinomial probit estimation. Covariates are differenced against the base alternative, so the design matrix has one row per (choice situation, non-base alternative) pair. Balanced choice sets are required: every choice situation must contain the same J alternatives.

Usage

prepare_mnp_data(
  data,
  id_col,
  alt_col,
  choice_col,
  covariate_cols,
  base_alt = NULL,
  use_asc = TRUE
)

Arguments

data	Data frame containing choice data.
id_col	Name of the column identifying choice situations (individuals).
alt_col	Name of the column identifying alternatives.
choice_col	Name of the column indicating chosen alternative (1 = chosen, 0 = not chosen).
covariate_cols	Vector of names of columns to be used as covariates.
base_alt	Label of the base (reference) alternative used for utility differencing. If NULL (default), the first alternative in sort order is used.
use_asc	Logical indicating whether to include alternative-specific constants (one intercept per non-base alternative).

Value

A list containing:

• X: Stacked differenced design matrix ((N * p) x K), covariate columns first, then ASC columns when use_asc = TRUE.

• y: Integer vector of choices (0 = base alternative, j in 1..p for the j-th non-base alternative), one per choice situation.

• p: Number of utility differences (J - 1).

• J: Number of alternatives.

• N: Number of choice situations.

• K: Number of columns of X.

• alt_mapping: Data.table mapping alternatives to summary statistics (the base alternative is alt_int = 1).

• base_alt: Resolved label of the base alternative.

• param_map: Named list of integer index vectors (beta, asc).

• use_asc: Logical flag.

• dropped_cols: Names of columns dropped due to collinearity, if any.

• data_spec: List with column name metadata.

Examples

library(data.table)
set.seed(42)
N <- 50; J <- 3
dt <- data.table(id = rep(1:N, each = J), alt = rep(1:J, N))
dt[, `:=`(x1 = rnorm(.N), x2 = rnorm(.N))]
dt[, choice := 0L]
dt[, choice := sample(c(1L, rep(0L, J - 1))), by = id]
input <- prepare_mnp_data(dt, "id", "alt", "choice", c("x1", "x2"))
str(input$X)
input$alt_mapping

choicer documentation built on Sept. 5, 2026, 1:07 a.m.