PseudoL {SemiPar.depCens}

Likelihood function under dependent censoring

Description

The PseudoL function is maximized in order to estimate the finite dimensional model parameters, including the dependency parameter. This function assumes that the cumulative hazard function is known.

Usage

PseudoL(theta, resData, X, W, lhat, cumL, cop, dist)

Arguments

theta

Estimated parameter values/initial values for finite dimensional parameters

resData

Data matrix with three columns; Z = the observed survival time, d1 = the censoring indicator of T and d2 = the censoring indicator of C.

X

Data matrix with covariates related to T

W

Data matrix with covariates related to C. First column of W should be ones

lhat

The estimated hazard function obtained from the output of SolveL.

cumL

The estimated cumulative hazard function from the output of SolveL.

cop

Which copula should be computed to account for dependency between T and C. This argument can take one of the values from c("Gumbel", "Frank", "Normal"). The default copula model is "Frank".

dist

The distribution to be used for the dependent censoring C. Only two distributions are allowed, i.e, Weibull and lognormal distributions. With the value "Weibull" as the default.

Value

maximized log-likelihood value