support_npmsm: Numerically find the support of the transitions from a...

In icmstate: Interval Censored Multi-State Models

Numerically find the support of the transitions from a converged npmsm algorithm

Description

For each transition in tmat, determine all consecutive bins with non-zero (higher than cutoff) transition intensities. These then determine the numerical support of the transition.

Usage

support_npmsm(npmsm, cutoff = 1e-08)

Arguments

npmsm	Output from npmsm function or an msfit object.
cutoff	Above which value is a mass in a bin considered to be non-zero? Default = 1e-8. Note that this is independent of bin size, so can be tricky!!

Value

A list containing a list for each transition. Each transition specific list contains the support intervals for that transition in a matrix with 3 named columns L, R and dA, indicating the left/right-endpoints of the support intervals and the change in the estimated intensities over this support interval.

Examples

require(mstate)
require(ggplot2)
#Generate from an illness-death model with exponential transitions with 
#rates 1/2, 1/10 and 1 for 10 subjects over a time grid.
gd <- sim_weibmsm(tmat = trans.illdeath(), shape = c(1,1,1),
                  scale = c(2, 10, 1), n_subj = 10, obs_pars = c(2, 0.5, 20), 
                  startprobs = c(0.9, 0.1, 0))
#Fit 2 models: 1 with at most 4 iterations and 1 with at most 20
mod1 <- npmsm(gd, trans.illdeath(), maxit = 4)

#Determine support numerically:
mod1_supp <- support_npmsm(mod1)
mod1_supp[[1]]

icmstate documentation built on April 3, 2025, 8:06 p.m.