Conditional prior proposals in dynamic models

Dynamic models extend state space models to non-normal observations. This p aper suggests a specific hybrid Metropolis-Hastings algorithm as a simple d evice for Bayesian inference via Markov chain Monte Carlo in dynamic models , Hastings proposals from the (conditional) prior distribution of the unkno wn, time-varying parameters are used to update the corresponding full condi tional distributions. It is shown through simulated examples that the metho dology has optimal performance in situations where the prior is relatively strong compared to the likelihood. Typical examples include smoothing prior s for categorical data. A specific blocking strategy is proposed to ensure good mixing and convergence properties of the simulated Markov chain. It is also shown that the methodology is easily extended to robust transition mo dels using mixtures of normals. The applicability is illustrated with an an alysis of a binomial and a binary time series, known in the literature.