Transition probability matrix from an msmbayes model

Transition probability matrix from an msmbayes model

Usage

pmatrix(
  draws,
  t = 1,
  new_data = NULL,
  states = "obs",
  X = NULL,
  drop = TRUE,
  type = "posterior"
)

Arguments

draws

Object returned by msmbayes.

t

prediction time or vector of prediction times

new_data

Data frame with covariate values to predict for

states

If states="obs" (or "observed") then this describes mean sojourn times in the observable states. For phase-type models this is not generally equal to the sum of the phase-specific mean sojourn times, because an individual may transition out of the state before progressing to the next phase.

If states="phase" (or "true", or "latent") then for phase-type models, this describes mean sojourn times in the latent state space.

X

Lower-level alternative to specifying new_data, for developer use only. X is a numeric matrix formed from column-binding the covariate design matrices for each transition in turn.

drop

Only used if there are no covariates supplied in new_data. Then if drop=TRUE this returns a nstates x nstates matrix, or if drop=FALSE this returns a 3D array with first dimension ncovs=1.

type

"posterior" to return rvar objects containing posterior samples.

"mode" to return posterior modes (only applicable if model was fitted with posterior mode optimisation).

Value

Array or matrix of rvar objects giving the transition probability matrix at each requested prediction time and covariate value. See qdf for notes on the rvar format.

For phase-type models, if states="obs", so that we want transition probabilities on the observable space, this returns the probability of transition to any phase of each "destination" state, for an individual who is in the first phase of each "starting" state.

See also

pmatrixdf returns the same information in a tidy data frame format.