startSS

It calculates sensible starting values for bivariate probit 
models with non-random sample selection. This is based on an adaptation of the Heckman two-step procedure.

Routine for fitting bivariate models for binary responses with semiparametric predictors (including linear and nonlinear effects) in the presence of correlated error equations, endogeneity, non-random sample selection or partial observability.

startSS: Internal Function

Description

Arguments

References