使用马尔可夫链蒙特卡罗计算的德·菲内蒂先验
de Finetti Priors using Markov chain Monte Carlo computations.
作者信息
Bacallado Sergio, Diaconis Persi, Holmes Susan
机构信息
Sequoia Hall, Stanford University.
出版信息
Stat Comput. 2015 Jul 1;25(4):797-808. doi: 10.1007/s11222-015-9562-9.
Abstract
Recent advances in Monte Carlo methods allow us to revisit work by de Finetti who suggested the use of approximate exchangeability in the analyses of contingency tables. This paper gives examples of computational implementations using Metropolis Hastings, Langevin and Hamiltonian Monte Carlo to compute posterior distributions for test statistics relevant for testing independence, reversible or three way models for discrete exponential families using polynomial priors and Gröbner bases.
摘要
蒙特卡罗方法的最新进展使我们能够重新审视德·菲内蒂的工作，他建议在列联表分析中使用近似可交换性。本文给出了使用梅特罗波利斯·黑斯廷斯算法、朗之万算法和哈密顿蒙特卡罗算法进行计算实现的示例，以计算与检验独立性、离散指数族的可逆或三向模型相关的检验统计量的后验分布，这些模型使用多项式先验和格罗比纳基。
相似文献
1
de Finetti Priors using Markov chain Monte Carlo computations.使用马尔可夫链蒙特卡罗计算的德·菲内蒂先验
Stat Comput. 2015 Jul 1;25(4):797-808. doi: 10.1007/s11222-015-9562-9.
2
On free energy barriers in Gaussian priors and failure of cold start MCMC for high-dimensional unimodal distributions.在高斯先验中的自由能障碍和高维单峰分布的冷启动 MCMC 的失败。
Philos Trans A Math Phys Eng Sci. 2023 May 15;381(2247):20220150. doi: 10.1098/rsta.2022.0150. Epub 2023 Mar 27.
3
A general construction for parallelizing Metropolis-Hastings algorithms.一种并行化 Metropolis-Hastings 算法的通用构造。
Proc Natl Acad Sci U S A. 2014 Dec 9;111(49):17408-13. doi: 10.1073/pnas.1408184111. Epub 2014 Nov 24.
4
Applying diffusion-based Markov chain Monte Carlo.应用基于扩散的马尔可夫链蒙特卡罗方法。
PLoS One. 2017 Mar 16;12(3):e0173453. doi: 10.1371/journal.pone.0173453. eCollection 2017.
5
Fast Bayesian whole-brain fMRI analysis with spatial 3D priors.具有空间3D先验的快速贝叶斯全脑功能磁共振成像分析。
Neuroimage. 2017 Feb 1;146:211-225. doi: 10.1016/j.neuroimage.2016.11.040. Epub 2016 Nov 19.
6
A review of the Bayesian approach with the MCMC and the HMC as a competitor of classical likelihood statistics for pharmacometricians.为药理学家回顾贝叶斯方法，其中马尔可夫链蒙特卡罗（MCMC）和哈密顿蒙特卡罗（HMC）作为经典似然统计的竞争对手。
Transl Clin Pharmacol. 2023 Jun;31(2):69-84. doi: 10.12793/tcp.2023.31.e9. Epub 2023 Jun 26.
7
A Monte Carlo Metropolis-Hastings algorithm for sampling from distributions with intractable normalizing constants.一种用于从具有难以处理的归一化常数的分布中进行抽样的蒙特卡罗 metropolis-hastings 算法。
Neural Comput. 2013 Aug;25(8):2199-234. doi: 10.1162/NECO_a_00466. Epub 2013 Apr 22.
8
Bayesian Trend Filtering via Proximal Markov Chain Monte Carlo.通过近端马尔可夫链蒙特卡罗方法实现的贝叶斯趋势滤波
J Comput Graph Stat. 2023;32(3):938-949. doi: 10.1080/10618600.2023.2170089. Epub 2023 Mar 2.
9
Parallel Metropolis coupled Markov chain Monte Carlo for Bayesian phylogenetic inference.用于贝叶斯系统发育推断的并行 metropolis 耦合马尔可夫链蒙特卡罗方法
Bioinformatics. 2004 Feb 12;20(3):407-15. doi: 10.1093/bioinformatics/btg427. Epub 2004 Jan 22.
10
A simple introduction to Markov Chain Monte-Carlo sampling.马尔可夫链蒙特卡罗采样简介。
Psychon Bull Rev. 2018 Feb;25(1):143-154. doi: 10.3758/s13423-016-1015-8.
引用本文的文献
1
Sparse graphs using exchangeable random measures.使用可交换随机测度的稀疏图。
J R Stat Soc Series B Stat Methodol. 2017 Nov;79(5):1295-1366. doi: 10.1111/rssb.12233. Epub 2017 Sep 23.
2
Matchings and phylogenetic trees.匹配与系统发育树。
Proc Natl Acad Sci U S A. 1998 Dec 8;95(25):14600-2. doi: 10.1073/pnas.95.25.14600.
本文引用的文献
1
Denoising PCR-amplified metagenome data.对 PCR 扩增的宏基因组数据进行去噪。
BMC Bioinformatics. 2012 Oct 31;13:283. doi: 10.1186/1471-2105-13-283.
2
Death has a preference for birthdays-an analysis of death time series.生日与死亡有关联——死亡时间序列分析
Ann Epidemiol. 2012 Aug;22(8):603-6. doi: 10.1016/j.annepidem.2012.04.016. Epub 2012 Jun 1.
3
The choice of statistical tests illustrated on the interpretation of data classed in a 2 X 2 table.统计检验的选择在2×2表格分类数据的解释中得到说明。
Biometrika. 1947;34(1-2):139-69. doi: 10.1093/biomet/34.1-2.139.
4
Frequentist performance of Bayesian confidence intervals for comparing proportions in 2 x 2 contingency tables.2×2列联表中用于比较比例的贝叶斯置信区间的频率主义性能
Biometrics. 2005 Jun;61(2):515-23. doi: 10.1111/j.1541-0420.2005.031228.x.
Zotero 插件