Estimate the NPMLE of censored data using the ISDM method proposed in Lesperance and Kalbfleisch (19
ISDM is a method for estimating the NPMLE of censored data.
ISDM(A, pvec, maxiter=500, tol=1e-07, tolbis=1e-08, verbose=FALSE)
A |
The m by n incidence, or clique, matrix. Or the n by 2 matrix containing the event intervals. |
pvec |
An initial estimate of the probability vector; not required. |
maxiter |
Maximum number of iterations to be made. |
tol |
The tolerance used to determine convergence. |
tolbis |
A second tolerance used for the steps. |
verbose |
Boolean, should verbose output be printed. |
Lots of complicated stuff should go here.
A list containing:
pf |
The estimated NPMLE of the probability vector. |
numiter |
The number of iterations performed. |
Alain Vandal and Robert Gentleman
An Algorithm for Computing the Nonparametric MLE of a Mixing Distribution, Lesperance, Mary L. and Kalbfleisch, John D., JASA, 1992
data(cosmesis)
csub1 <- subset(cosmesis, subset=Trt==0, select=c(L,R))
ISDM(csub1)
# data(pruitt)
# ISDM(pruitt)Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.