A comparison of centring parameterisations of Gaussian process-based models for Bayesian computation using MCMC

A comparison of centring parameterisations of Gaussian process-based models for Bayesian computation using MCMC
复制标题

使用 MCMC 进行贝叶斯计算的基于高斯过程的模型的中心参数化比较

DOI:
10.1007/s11222-016-9700-z
复制
发表时间:
2016
影响因子:
2.2
通讯作者:
Bass M
Bass M
中科院分区:
数学2区
文献类型:
--
作者:
Bass M

文献摘要

参考文献

被引文献

相似文献

马尔可夫链蒙特卡罗(MCMC)算法用于基于高斯过程模型的贝叶斯计算,在缺省参数条件下,由于空间和其他诱导的依赖结构的存在,收敛速度很慢。本文主要研究在缺省非中心参数化和竞争中心参数化(CP)下,对于一般多过程高斯空间模式的平均结构,假设的空间相关结构对Gibbs采样器收敛特性的影响。我们的调查找到了关于两者之间选择的许多相关但尚未得到回答的问题的答案。假设协方差参数已知,我们通过改变空间相关性的强度、协方差缩减的程度、空间变化的协变量的规模、数据点的数量、空间效应的块更新的数量和结构以及在Matérn协方差函数中假设的光滑量来比较两者的精确收敛速度。我们还研究了在空间模型中引入不同程度的几何各向异性的影响。利用著名的MCMC收敛诊断方法研究了方差参数未知的情况。以模拟伦敦空气污染水平的模拟研究和实际数据为例进行了说明。出现了一种普遍的模式,即当存在更多的空间相关性或通过例如额外的数据点或通过增加的协变量变异性获得的更多信息时,CP更可取。
Markov chain Monte Carlo (MCMC) algorithms for Bayesian computation for Gaussian process-based models under default parameterisations are slow to converge due to the presence of spatial- and other-induced dependence structures. The main focus of this paper is to study the effect of the assumed spatial correlation structure on the convergence properties of the Gibbs sampler under the default non-centred parameterisation and a rival centred parameterisation (CP), for the mean structure of a general multi-process Gaussian spatial model. Our investigation finds answers to many pertinent, but as yet unanswered, questions on the choice between the two. Assuming the covariance parameters to be known, we compare the exact rates of convergence of the two by varying the strength of the spatial correlation, the level of covariance tapering, the scale of the spatially varying covariates, the number of data points, the number and the structure of block updating of the spatial effects and the amount of smoothness assumed in a Matérn covariance function. We also study the effects of introducing differing levels of geometric anisotropy in the spatial model. The case of unknown variance parameters is investigated using well-known MCMC convergence diagnostics. A simulation study and a real-data example on modelling air pollution levels in London are used for illustrations. A generic pattern emerges that the CP is preferable in the presence of more spatial correlation or more information obtained through, for example, additional data points or by increased covariate variability.
DOI: 10.1198/016214507000000031
发表时间: 2007-12-01
影响因子: 3.7
作者:
Sahu, Sujit K.;Gelfand, Alan E.;Holland, David M.
通讯作者: Holland, David M.
使用各向异性高斯随机场对西澳大利亚极端降水进行时空分层建模
DOI: --
发表时间: 2013
影响因子: 3.8
作者:
P. Apputhurai;A. Stephenson
通讯作者: A. Stephenson
贝叶斯分层模型吉布斯采样器的稳定性
DOI: --
发表时间: 2007
期刊:
影响因子: --
作者:
O. Papaspiliopoulos;G. Roberts
通讯作者: G. Roberts
DOI: 10.1198/016214508000000959
发表时间: 2008-12-01
影响因子: 3.7
作者:
Kaufman, Cari G.;Schervish, Mark J.;Nychka, Douglas W.
通讯作者: Nychka, Douglas W.
用于分层模型和数据增强的非中心参数化。
DOI: --
发表时间: 2003
期刊:
影响因子: --
作者:
G. Roberts;O. Papaspiliopoulos;M. Sköld
通讯作者: M. Sköld