Poisson hidden Markov model

In statistics, Poisson hidden Markov models (PHMM) are a special case of hidden Markov models where a Poisson process has a rate which varies in association with changes between the different states of a Markov model. PHMMs are not necessarily Markovian processes themselves because the underlying Markov chain or Markov process cannot be observed and only the Poisson signal is observed.

See also

• Doubly stochastic model
• Cox process

References

• R. Paroli. et al., Poisson hidden Markov models for time series of overdispersed insurance counts