bprobgHsSS

It provides the log-likelihood, gradient and observed information matrix for 
penalized or unpenalized maximum likelihood optimization, for the non-random sample selection model case. Possible bivariate distributions are bivariate normal, Clayton, rotated Clayton (90 degrees), survival Clayton, rotated Clayton (270 degrees), Joe, rotated Joe (90 degrees), survival Joe, rotated Joe (270 degrees), Gumbel, rotated Gumbel (90 degrees), survival Gumbel, rotated Gumbel (270 degrees), and Frank. For the normal case only, the Fisher information is also available.

Routine for fitting bivariate probit models with semiparametric predictors (including linear, nonlinear and random effects) in the presence of correlated error equations, endogeneity or sample selection. Bivariate copula models are also supported.

bprobgHsSS: Internal Function

Description

Arguments

References