You are not currently logged in.
Access your personal account or get JSTOR access through your library or other institution:
If You Use a Screen ReaderThis content is available through Read Online (Free) program, which relies on page scans. Since scans are not currently available to screen readers, please contact JSTOR User Support for access. We'll provide a PDF copy for your screen reader.
Choice of Initial States in Estimating Transition Probabilities of a Finite Ergodic Markov Chain
B. R. Handa
Vol. 59, No. 2 (Aug., 1972), pp. 407-414
Stable URL: http://www.jstor.org/stable/2334585
Page Count: 8
Since scans are not currently available to screen readers, please contact JSTOR User Support for access. We'll provide a PDF copy for your screen reader.
Preview not available
The properties of the maximum likelihood estimators for the transition probabilities in a two-stage ergodic Markov chain depend upon the choice of the initial states. For example, the initial states may be suitably fixed in advance or may be observed from the equilibrium distribution of the chain. A large number of relatively short realizations are assumed available and the asymptotic variances are examined in some detail. The relevant asymptotic covariance matrices are derived also for the s-state chain.
Biometrika © 1972 Biometrika Trust