lb_ipopt {lb}R Documentation

Fitting Log-Binomial Models with ipoptr

Description

Fitting Log-Binomial Models with ipoptr

Usage

lb_ipopt(x, y, start, tol = 1e-08, ceps = 1e-07, control = list())

Arguments

x

design matrix of dimension n * p.

y

vector of observations of length n.

start

numeric (vector) starting value (of length p).

tol

a numeric giving the tolerance for convergence of the outer iterations (see eps in control.outer the from the auglag function.

ceps

epsilon subtracted from the right hand side (X β ≤q 0 - ceps). Since the inequality X β ≤q 0 is only fullfilled to a certain tolerance we have to substact epsilon to ensure X β ≤q 0.

control

passed to control.outer.

Value

the optimization result.


[Package lb version 1.1 Index]