用于疾病地图绘制的空间依赖贝叶斯模型选择
Spatially-dependent Bayesian model selection for disease mapping.
作者信息
Carroll Rachel, Lawson Andrew B, Faes Christel, Kirby Russell S, Aregay Mehreteab, Watjou Kevin
机构信息
1 Department of Public Health, Medical University of South Carolina, Charleston, SC, USA.
2 Interuniversity Institute for Statistics and statistical Bioinformatics, Hasselt University, Diepenbeek, Belgium.
出版信息
Stat Methods Med Res. 2018 Jan;27(1):250-268. doi: 10.1177/0962280215627298. Epub 2016 Jul 20.
Abstract
In disease mapping where predictor effects are to be modeled, it is often the case that sets of predictors are fixed, and the aim is to choose between fixed model sets. Model selection methods, both Bayesian model selection and Bayesian model averaging, are approaches within the Bayesian paradigm for achieving this aim. In the spatial context, model selection could have a spatial component in the sense that some models may be more appropriate for certain areas of a study region than others. In this work, we examine the use of spatially referenced Bayesian model averaging and Bayesian model selection via a large-scale simulation study accompanied by a small-scale case study. Our results suggest that BMS performs well when a strong regression signature is found.
摘要
在疾病映射中，若要对预测因子的效应进行建模，通常情况下预测因子集是固定的，目标是在固定的模型集中进行选择。模型选择方法，包括贝叶斯模型选择和贝叶斯模型平均，都是贝叶斯范式中用于实现这一目标的方法。在空间背景下，模型选择可能具有空间成分，即某些模型可能比其他模型更适用于研究区域的某些特定区域。在这项工作中，我们通过一项大规模模拟研究并辅以一项小规模案例研究，考察了空间参考贝叶斯模型平均和贝叶斯模型选择的应用。我们的结果表明，当发现强回归特征时，贝叶斯模型选择表现良好。
相似文献
1
Spatially-dependent Bayesian model selection for disease mapping.用于疾病地图绘制的空间依赖贝叶斯模型选择
Stat Methods Med Res. 2018 Jan;27(1):250-268. doi: 10.1177/0962280215627298. Epub 2016 Jul 20.
2
Model selection in medical research: a simulation study comparing Bayesian model averaging and stepwise regression.医学研究中的模型选择：贝叶斯模型平均与逐步回归比较的模拟研究。
BMC Med Res Methodol. 2010 Dec 6;10:108. doi: 10.1186/1471-2288-10-108.
3
Spatio-temporal Bayesian model selection for disease mapping.用于疾病地图绘制的时空贝叶斯模型选择
Environmetrics. 2016 Dec;27(8):466-478. doi: 10.1002/env.2410. Epub 2016 Sep 28.
4
Comparison of Bayesian model averaging and stepwise methods for model selection in logistic regression.逻辑回归中用于模型选择的贝叶斯模型平均法与逐步法的比较
Stat Med. 2004 Nov 30;23(22):3451-67. doi: 10.1002/sim.1930.
5
Comparing INLA and OpenBUGS for hierarchical Poisson modeling in disease mapping.比较INLA和OpenBUGS在疾病地图分层泊松模型中的应用
Spat Spatiotemporal Epidemiol. 2015 Jul-Oct;14-15:45-54. doi: 10.1016/j.sste.2015.08.001. Epub 2015 Aug 11.
6
Bayesian model selection methods in modeling small area colon cancer incidence.用于小区域结肠癌发病率建模的贝叶斯模型选择方法
Ann Epidemiol. 2016 Jan;26(1):43-9. doi: 10.1016/j.annepidem.2015.10.011. Epub 2015 Nov 14.
7
On identification in Bayesian disease mapping and ecological-spatial regression models.贝叶斯疾病映射与生态空间回归模型中的识别问题。
Stat Methods Med Res. 2014 Apr;23(2):134-55. doi: 10.1177/0962280212447152. Epub 2012 May 8.
8
Bayesian spatially dependent variable selection for small area health modeling.用于小区域健康建模的贝叶斯空间相关变量选择
Stat Methods Med Res. 2018 Jan;27(1):234-249. doi: 10.1177/0962280215627184. Epub 2016 Jun 16.
9
Bayesian detection and modeling of spatial disease clustering.空间疾病聚集性的贝叶斯检测与建模
Biometrics. 2000 Sep;56(3):922-35. doi: 10.1111/j.0006-341x.2000.00922.x.
10
Spatial correlation in Bayesian logistic regression with misclassification.存在误分类情况下贝叶斯逻辑回归中的空间相关性。
Spat Spatiotemporal Epidemiol. 2014 Jun;9:1-12. doi: 10.1016/j.sste.2014.02.002. Epub 2014 Mar 1.
引用本文的文献
1
Spatiotemporal patterns and association with climate for malaria elimination in Lao PDR: a hierarchical modelling analysis with two-step Bayesian model selection.老挝消除疟疾的时空模式及其与气候的关联：两步贝叶斯模型选择的分层建模分析。
Malar J. 2024 Aug 4;23(1):231. doi: 10.1186/s12936-024-05064-0.
2
Two-step spatiotemporal anomaly detection corrected for lag reporting time with application to real-time dengue surveillance in Thailand.两步时空异常检测校正滞后报告时间，并应用于泰国的实时登革热监测。
BMC Med Res Methodol. 2024 Jan 13;24(1):10. doi: 10.1186/s12874-024-02141-5.
3
Projecting malaria elimination in Thailand using Bayesian hierarchical spatiotemporal models.利用贝叶斯分层时空模型预测泰国的疟疾消除情况。
Sci Rep. 2023 May 13;13(1):7799. doi: 10.1038/s41598-023-35007-9.
4
Spatiotemporal reproduction number with Bayesian model selection for evaluation of emerging infectious disease transmissibility: an application to COVID-19 national surveillance data.贝叶斯模型选择的时空繁殖数评估新发传染病的传染性：在 COVID-19 国家监测数据中的应用。
BMC Med Res Methodol. 2023 Mar 14;23(1):62. doi: 10.1186/s12874-023-01870-3.
5
Bayesian spatio-temporal distributed lag modeling for delayed climatic effects on sparse malaria incidence data.贝叶斯时空分布滞后模型在稀疏疟疾发病率数据中对滞后气候效应的应用。
BMC Med Res Methodol. 2021 Dec 20;21(1):287. doi: 10.1186/s12874-021-01480-x.
6
Spatiotemporal multivariate mixture models for Bayesian model selection in disease mapping.用于疾病地图绘制中贝叶斯模型选择的时空多元混合模型
Environmetrics. 2017 Dec;28(8). doi: 10.1002/env.2465. Epub 2017 Sep 25.
7
Spatio-temporal Bayesian model selection for disease mapping.用于疾病地图绘制的时空贝叶斯模型选择
Environmetrics. 2016 Dec;27(8):466-478. doi: 10.1002/env.2410. Epub 2016 Sep 28.
8
Bayesian model selection methods in modeling small area colon cancer incidence.用于小区域结肠癌发病率建模的贝叶斯模型选择方法
Ann Epidemiol. 2016 Jan;26(1):43-9. doi: 10.1016/j.annepidem.2015.10.011. Epub 2015 Nov 14.
本文引用的文献
1
Negotiating Multicollinearity with Spike-and-Slab Priors.利用尖劈板先验处理多重共线性
Metron. 2014 Aug 1;72(2):217-229. doi: 10.1007/s40300-014-0047-y.
2
Associations of census-tract poverty with subsite-specific colorectal cancer incidence rates and stage of disease at diagnosis in the United States.美国普查区贫困状况与特定亚部位结直肠癌发病率及诊断时疾病分期的关联。
J Cancer Epidemiol. 2014;2014:823484. doi: 10.1155/2014/823484. Epub 2014 Aug 3.
3
A Bayesian hierarchical model with spatial variable selection: the effect of weather on insurance claims.一种具有空间变量选择的贝叶斯层次模型：天气对保险理赔的影响。
J R Stat Soc Ser C Appl Stat. 2013 Jan;62(1):85-100. doi: 10.1111/j.1467-9876.2012.01039.x.
4
Spatial variation in stage distribution in colorectal cancer in the Netherlands.荷兰结直肠癌分期分布的空间差异。
Eur J Cancer. 2012 May;48(8):1119-25. doi: 10.1016/j.ejca.2011.06.058. Epub 2011 Jul 29.
5
Assessing Local Model Adequacy in Bayesian Hierarchical Models Using the Partitioned Deviance Information Criterion.使用分区偏差信息准则评估贝叶斯层次模型中的局部模型适用性。
Comput Stat Data Anal. 2010 Jun 1;54(6):1657-1671. doi: 10.1016/j.csda.2010.01.025.
6
The Bayesian lasso for genome-wide association studies.贝叶斯套索在全基因组关联研究中的应用。
Bioinformatics. 2011 Feb 15;27(4):516-23. doi: 10.1093/bioinformatics/btq688. Epub 2010 Dec 14.
7
VARIABLE SELECTION FOR REGRESSION MODELS WITH MISSING DATA.针对存在缺失数据的回归模型的变量选择
Stat Sin. 2010 Jan;20(1):149-165.
8
Joint variable selection for fixed and random effects in linear mixed-effects models.线性混合效应模型中固定效应和随机效应的联合变量选择
Biometrics. 2010 Dec;66(4):1069-77. doi: 10.1111/j.1541-0420.2010.01391.x.
9
Spatial analysis of colorectal cancer incidence and proportion of late-stage in Massachusetts residents: 1995-1998.马萨诸塞州居民结直肠癌发病率及晚期比例的空间分析：1995 - 1998年
Int J Health Geogr. 2007 Jun 4;6:20. doi: 10.1186/1476-072X-6-20.
10
Variable selection and Bayesian model averaging in case-control studies.病例对照研究中的变量选择与贝叶斯模型平均法
Stat Med. 2001 Nov 15;20(21):3215-30. doi: 10.1002/sim.976.
Zotero 插件