Loading Events

Sergio Bacallado (Stanford University)

23 September 2011 @ 12:00

 

  • Past event

Details

Date:
23 September 2011
Time:
12:00
Event Category:

A Bayesian analysis of reversible time series with an uncertain length of memory

We propose a Bayesian analysis of reversible time series using a Probabilistic Suffix Automaton (PSA) model. We show that PSAs have a representation as higher-order Markov chains, and that the class of reversible PSAs generalize reversible variable-order Markov chains. The analysis uses a conjugate prior for higher-order Markov chains (Bacallado, Annals of Statistics, 39 (2), 2011), which allows us to sample the posterior of the process and latent lengths of memory through a blocked Gibbs sampler. We show the application of the method to a dataset of molecular dynamics simulations of protein folding.