An S-plus implementation of hidden Markov models in continuous time

Hidden Markov models (HMM) can be applied to the study of time varying unob served categorical Variables for which only indirect measurements are avail able. An S-Plus module to fit HMMs in continuous time to this type of longi tudinal data is presented. Covariates affecting the transition intensities of the hidden Markov process or the conditional distribution of the measure d response (given the hidden states of the process) are handled under a gen eralized regression framework. Users can provide C subroutines specifying t he parameterization of the model to adapt the software to a wide variety of data types. HMM analysis using the S-Plus module is illustrated on a datas et from a prospective study of human papillomavirus infection in young wome n and on simulated data.