Abstract | ||
---|---|---|
Summary. We analyze a hierarchical Bayes model which is related to the usual empirical Bayes formulation of James-Stein estimators. We consider running a Gibbs sampler on this model. Using previous results about convergence rates of Markov chains, we provide rigorous, numerical, reasonable bounds on the running time of the Gibbs sampler, for a suitable range of prior distributions. We apply these results to baseball data from Efron and Morris (1975). For a dierent range of prior distributions, we prove that the Gibbs sampler will fail to converge, and use this information to prove that in this case the associated posterior distribution is non-normalizable. |
Year | DOI | Venue |
---|---|---|
1996 | https://doi.org/10.1007/BF00140871 | Statistics and Computing |
Keywords | Field | DocType |
Convergence rate,James-Stein estimator,Gibbs sampler,Markov chain Monte Carlo | James–Stein estimator,Markov chain Monte Carlo,Markov chain,Posterior probability,Rate of convergence,Statistics,Mathematics,Gibbs sampling,Estimator,Bayes' theorem | Journal |
Volume | Issue | ISSN |
6 | 3 | 0960-3174 |
Citations | PageRank | References |
4 | 1.34 | 1 |
Authors | ||
1 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jeffrey S. Rosenthal | 1 | 357 | 43.06 |