wfunk {eha}R Documentation

Loglihood function of a Weibull regression

Description

Calculates minus the log likelihood function and its first and second order derivatives for data from a Weibull regression model. Is called by weibreg.

Usage

wfunk(beta = NULL, lambda, p, X = NULL, Y, offset = rep(0, length(Y)),
ord = 2, pfixed = FALSE)

Arguments

beta Regression parameters
lambda The scale paramater
p The shape parameter
X The design (covariate) matrix.
Y The response, a survival object.
offset Offset.
ord ord = 0 means only loglihood, 1 means score vector as well, 2 loglihood, score and hessian.
pfixed Logical, if TRUE the shape parameter is regarded as a known constant in the calculations, meaning that it is not cosidered in the partial derivatives.

Details

Note that the function returns log likelihood, score vector and minus hessian, i.e. the observed information. The model is

h(t; p, λ, β, z) = p / λ (t / λ)^{(p-1)}exp{(-( t / λ)^p}) exp(zβ)

This is in correspondence with dweibull.

Value

A list with components

f The log likelihood. Present if ord >= 0
fp The score vector. Present if ord >= 1
fpp The negative of the hessian. Present if ord >= 2

Author(s)

Göran Broström

See Also

weibreg


[Package eha version 1.2-4 Index]