The BUGS project: Evolution, critique and future directions

被引:1449
作者
Lunn, David [1 ]
Spiegelhalter, David [1 ]
Thomas, Andrew [2 ]
Best, Nicky [3 ]
机构
[1] Inst Publ Hlth, MRC, Biostat Unit, Cambridge CB2 0SR, England
[2] Sch Math & Stat, Math Inst, St Andrews KY16 9SS, Fife, Scotland
[3] Univ London Imperial Coll Sci Technol & Med, Dept Epidemiol & Publ Hlth, London W2 1PG, England
基金
英国医学研究理事会;
关键词
BUGS; WinBUGS; OpenBUGS; Bayesian modelling; graphical models; PROBABILITIES; MODELS;
D O I
10.1002/sim.3680
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
BUGS is a software package for Bayesian inference using Gibbs sampling. The software has been instrumental in raising awareness of Bayesian modelling among both academic and commercial communities internationally, and has enjoyed considerable Success over its 20-year life span. Despite this, the software has a number of shortcomings and a principal aim of this paper is to provide a balanced critical appraisal, in particular highlighting how various ideas have led to unprecedented flexibility while at the same time producing negative side effects. We also present a historical overview of the BUGS project and some future perspectives. Copyright (C) 2009 John Wiley & Sons, Ltd.
引用
收藏
页码:3049 / 3067
页数:19
相关论文
共 61 条
[1]  
[Anonymous], 2003, MAT BIO MED
[2]  
[Anonymous], 2008, JAGS VERSION 1 0 3 M
[3]  
[Anonymous], 2011, Data analysis using regression and multilevel/hierarchical models
[4]  
[Anonymous], 2008, SAS/STAT 9.2 user's guide
[5]  
[Anonymous], ISBA B
[6]  
[Anonymous], 2001, BAYESIAN STAT MODELL
[7]   IRT Modeling of Tutor Performance to Predict End-of-Year Exam Scores [J].
Ayers, Elizabeth ;
Junker, Brian .
EDUCATIONAL AND PSYCHOLOGICAL MEASUREMENT, 2008, 68 (06) :972-987
[8]  
Broemeling L.D., 2007, BAYESIAN BIOSTATISTI
[9]  
Carlin B.P., 2008, Bayesian methods for data analysis
[10]   Mixture models for classification [J].
Celeux, Gilles .
Advances in Data Analysis, 2007, :3-14