Mathematics – Probability
Scientific paper
2007-02-09
Annals of Applied Probability 2006, Vol. 16, No. 4, 1805-1815
Mathematics
Probability
Published at http://dx.doi.org/10.1214/105051606000000367 in the Annals of Applied Probability (http://www.imstat.org/aap/) by
Scientific paper
10.1214/105051606000000367
According to a 1975 result of T. Kaijser, if some nonvanishing product of hidden Markov model (HMM) stepping matrices is subrectangular, and the underlying chain is aperiodic, the corresponding $\alpha$-chain has a unique invariant limiting measure $\lambda$. Here the $\alpha$-chain $\{\alpha_n\}=\{(\alpha_{ni})\}$ is given by \[\alpha_{ni}=P(X_n=i| Y_n,Y_{n-1},...),\] where $\{(X_n,Y_n)\}$ is a finite state HMM with unobserved Markov chain component $\{X_n\}$ and observed output component $\{Y_n\}$. This defines $\{\alpha_n\}$ as a stochastic process taking values in the probability simplex. It is not hard to see that $\{\alpha_n\}$ is itself a Markov chain. The stepping matrices $M(y)=(M(y)_{ij})$ give the probability that $(X_n,Y_n)=(j,y)$, conditional on $X_{n-1}=i$. A matrix is said to be subrectangular if the locations of its nonzero entries forms a cartesian product of a set of row indices and a set of column indices. Kaijser's result is based on an application of the Furstenberg--Kesten theory to the random matrix products $M(Y_1)M(Y_2)... M(Y_n)$. In this paper we prove a slightly stronger form of Kaijser's theorem with a simpler argument, exploiting the theory of e chains.
Kochman Fred
Reeds Jim
No associations
LandOfFree
A simple proof of Kaijser's unique ergodicity result for hidden Markov $α$-chains does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with A simple proof of Kaijser's unique ergodicity result for hidden Markov $α$-chains, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and A simple proof of Kaijser's unique ergodicity result for hidden Markov $α$-chains will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-8327