Given an individual is currently in state \(r\), these are the probabilities that when leaving state \(r\), the individual will move to a particular state \(s\).
Arguments
- draws
Object returned by
msmbayes.- new_data
Data frame with covariate values to predict for
Details
In a Markov model, this is defined as the transition intensity from \(r\) to \(s\) divided by the sum of all transition intensities out of \(r\).
In semi-Markov models, this quantity is a model parameter in itself. In phase-type approximation models, the parameters consist of the parameters of the sojourn distribution and the next-state probabilities, which (as in a Markov model) are assumed to be independent of the sojourn time.
As the models in msmbayes work in continuous time, the
next-state probability is different from the transition
probability. The transition probability is the probability that
the individual is in state \(s\) at a specific time in the
future, and can be obtained from an msmbayes model with the
functions pdf, pmatrix.