oprobit_dist: Ordinal Probit Models

In mdmb: Model Based Treatment of Missing Data

Ordinal Probit Models

Description

Fits and evaluates the ordinal probit model.

Usage

#---- ordinal probit model
doprobit(x, thresh, max_val=99)

fit_oprobit(x, par_init=NULL, weights=NULL)
## S3 method for class 'fit_oprobit'
coef(object, ...)
## S3 method for class 'fit_oprobit'
logLik(object, ...)
## S3 method for class 'fit_oprobit'
summary(object, digits=4, file=NULL, ...)
## S3 method for class 'fit_oprobit'
vcov(object, ...)

Arguments

x	Numeric vector
thresh	Vector of thresholds
max_val	Maximum value for computing thresholds
par_init	Optional vector of initial parameters
weights	Optional vector of sampling weights
object	Object of class fit_yjt_scaled or fit_t_scaled
digits	Number of digits used for rounding in summary
file	File name for the summary to be sunk into
...	Further arguments to be passed

Value

Vector or an object of fitted distribution depending on the called function

See Also

See oprobit_regression for fitting a regression model in which the response variable follows an ordinal probit model.

Examples

#############################################################################
# EXAMPLE 1: Fit an ordinal probit distribution
#############################################################################

#-- simulate data
set.seed(987)
N <- 1500
# define thresholds
thresh <- c(0,.3, .7, 1.6)
# latent continuous data
yast <- stats::rnorm(N)
# discretized ordinal data
x <- as.numeric( cut( yast, c(-Inf,thresh,Inf) ) ) - 1

#-- fit ordinal probit distribution
mod <- mdmb::fit_oprobit(x=x)
summary(mod)
logLik(mod)
vcov(mod)

mdmb documentation built on March 7, 2023, 6:58 p.m.