Pseudo-Gibbs sampler for discrete conditional distributions
| العنوان: | Pseudo-Gibbs sampler for discrete conditional distributions |
|---|---|
| المؤلفون: | Kun-Lin Kuo, Yuchung J. Wang |
| المصدر: | Annals of the Institute of Statistical Mathematics. 71:93-105 |
| بيانات النشر: | Springer Science and Business Media LLC, 2017. |
| سنة النشر: | 2017 |
| مصطلحات موضوعية: | Statistics and Probability, Stationary distribution, 05 social sciences, Univariate, Conditional probability distribution, 01 natural sciences, Regression, Statistics::Computation, 010104 statistics & probability, symbols.namesake, Discriminative model, 0502 economics and business, Statistics, symbols, Statistics::Methodology, Applied mathematics, Imputation (statistics), 0101 mathematics, Marginal distribution, 050205 econometrics, Mathematics, Gibbs sampling |
| الوصف: | Conditionally specified models offers a higher level of flexibility than the joint approach. Regression switching in multiple imputation is a typical example. However, reasonable-seeming conditional models are generally not coherent with one another. Gibbs sampler based on incompatible conditionals is called pseudo-Gibbs sampler, whose properties are mostly unknown. This article investigates the richness and commonalities among their stationary distributions. We show that Gibbs sampler replaces the conditional distributions iteratively, but keep the marginal distributions invariant. In the process, it minimizes the Kullback–Leibler divergence. Next, we prove that systematic pseudo-Gibbs projections converge for every scan order, and the stationary distributions share marginal distributions in a circularly fashion. Therefore, regardless of compatibility, univariate consistency is guaranteed when the orders of imputation are circularly related. Moreover, a conditional model and its pseudo-Gibbs distributions have equal number of parameters. Study of pseudo-Gibbs sampler provides a fresh perspective for understanding the original Gibbs sampler. |
| تدمد: | 1572-9052 0020-3157 |
| URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_________::a226894fb78643e0b339154bccfd748c https://doi.org/10.1007/s10463-017-0625-x |
| حقوق: | CLOSED |
| رقم الأكسشن: | edsair.doi...........a226894fb78643e0b339154bccfd748c |
| قاعدة البيانات: | OpenAIRE |
Find this article in full text from Springer Verlag. | تدمد: | 15729052 00203157 |
|---|