Analysis of Multi-Type Recurrent Events
Akaike's Information Criterion
Bayesian Information Criteron
Collapse a vector into a string
Confidence Intervals for Model Parameters
Deviance of a fitted model
Return a vector of indices
Issue an error message and stop
Issue an error message and stop
Identity inverse link
Identity link
Get starting values for proportional hazards style likelihood
Calculate the likelihood)
Log Inverse link
Log likelihood of a fitted model
Log link
Construct a object returned by multiRec
Fit the multi-type recurrent event model
Return the number of indices assigned so far
Return the parameter vector
Collapse a vector into a string
Plot profile likelihoods
Print a short summary of the model fit
Reset the index offset
Initialize an empty parameter vector
Residuals from a fitted model
Set names for a part of the parameter vector
Set a part of the parameter vector
Variance covariance matrix of a fitted model
Issue a warning
Yeo-Johnson transformation with parameter k
Inverse Yeo-Johnson transformation with parameter k
Yeo-Johnson link
Inverse Yeo-Johnson link
Implements likelihood-based estimation and diagnostics for multi-type recurrent event data with dynamic risk that depends on prior events and accommodates terminating events. Methods are described in Ghosh, Chan, Younes and Davis (2023) "A Dynamic Risk Model for Multitype Recurrent Events" <doi:10.1093/aje/kwac213>.