Loglihood function of a Weibull regression

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

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.

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

Details

Note that the function returns log likelihood, score vector and minus hessian, i.e. the observed information. The model is $$h(t; p, \lambda,\beta, z) = p / \lambda (t / \lambda)^{(p-1)}\exp{(-( t / \lambda)^p})\exp(z\beta)$$ This is in correspondence with dweibull.

See also

weibreg

Author

Göran Broström