.\" DO NOT MODIFY THIS FILE!  It was generated by help2man 1.47.13.
.TH GBNLPROBIT "1" "June 2021" "gbnlprobit 6.2" "User Commands"
.SH NAME
gbnlprobit \- Non linear probit regression
.SH SYNOPSIS
.B gbnlprobit
[\fI\,options\/\fR] \fI\,<function definition>\/\fR
.SH DESCRIPTION
Non linear probit estimation. Minimize the negative log\-likelihood
.IP
sum_{i in N_0} log(1\-F(g(X_i))) + sum_{i in N_1} log(F(g(X_i)))
.PP
where N_0 and N_1 are the sets of 0 and 1 observations, g is a generic
function of the independent variables and F is the normal CDF. It is also
possible to minimize the score function
.PP
w_0 sum_{i in N_0} theta(F(g(X_i))\-t) +
.IP
w_1 sum_{i in N_1} theta(t\-F(g(X_i)))
.PP
where theta is the Heaviside function and t a threshold level. Weights
w_0 and w_1 scale the contribution of the two subpopulations. The first
column of data contains 0/1 entries. Successive columns are independent
variables. The model is specified by a function g(x1,x2...) where x1,..
stands for the first,second .. N\-th column independent variables.
.SS "options:"
.TP
\fB\-O\fR
type of output (default 0)
.TP
0
parameters
.TP
1
parameters and errors
.TP
2
<variables> and probabilities
.TP
3
parameters and variance matrix
.TP
4
marginal effects
.TP
\fB\-V\fR
variance matrix estimation (default 0)
.TP
0
<gradF gradF^t>
.TP
1
< J^{\-1} >
.TP
2
< H^{\-1} >
.TP
3
< H^{\-1} J H^{\-1} >
.TP
\fB\-z\fR
take zscore (not of 0/1 dummies)
.TP
\fB\-F\fR
input fields separators (default " \et")
.TP
\fB\-v\fR
verbosity level (default 0)
.TP
0
just results
.TP
1
comment headers
.TP
2
summary statistics
.TP
3
covariance matrix
.TP
4
minimization steps (default 10)
.TP
5
model definition
.TP
\fB\-g\fR
set number of point for global optimal threshold identification
.TP
\fB\-h\fR
this help
.TP
\fB\-t\fR
set threshold value (default 0)
.TP
0
ignore threshold
.TP
(0,1)
user provided threshold
.TP
1
compute optimal only global
.TP
2
compute optimal
.TP
\fB\-M\fR
estimation method
.TP
0
maximum likelihood
.TP
1
min. score (w0=w1=1)
.TP
2
min. score (w0=1/N0, w1=1/N1)
.TP
\fB\-A\fR
MLL optimization options (default 0.01,0.1,100,1e\-6,1e\-6,5)
fields are step,tol,iter,eps,msize,algo. Empty fields for default
.TP
step
initial step size of the searching algorithm
.TP
tol
line search tolerance iter: maximum number of iterations
.TP
eps
gradient tolerance : stopping criteria ||gradient||<eps
.TP
algo
optimization methods: 0 Fletcher\-Reeves, 1 Polak\-Ribiere,
2 Broyden\-Fletcher\-Goldfarb\-Shanno, 3 Steepest descent, 4 simplex
.TP
\fB\-B\fR
score optimization options (default 0.1,100,1e\-6)
fields are step,iter,msize. Empty fields for default
.TP
step
initial step size of the searching algorithm
.TP
iter
maximum number of iterations
.TP
msize
max size, stopping criteria simplex dim. <max size
optimization method is simplex
.SH AUTHOR
Written by Giulio Bottazzi
.SH "REPORTING BUGS"
Report bugs to <gbutils@googlegroups.com>
.PP
.br
Package home page <http://cafim.sssup.it/~giulio/software/gbutils/index.html>
.SH COPYRIGHT
Copyright \(co 2001\-2018 Giulio Bottazzi
This program is free software; you can redistribute it and/or
modify it under the terms of the GNU General Public License
(version 2) as published by the Free Software Foundation;
.PP
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
GNU General Public License for more details.