Bayesian model evidence as a practical alternative to deviance information criterion.
Bayesian model evidence as a practical alternative to deviance information criterion.
复制标题
DOI：
10.1098/rsos.171519
复制
发表时间：
2018-03
影响因子：
3.5
通讯作者：
Marion G
中科院分区：
文献类型：
--
作者：
Pooley CM;Marion G
虽然贝叶斯统计学家认为模型证据是模型选择的黄金标准（给出贝叶斯因子的两个模型之间的模型证据比例），但它的计算通常被认为对许多应用的计算要求太高。相比之下，广泛使用的偏差信息标准（DIC）是一种平衡模型准确性和复杂性的不同度量，通常被认为是一种更快的替代方法。然而，最近有效的多温度马尔可夫链蒙特卡罗算法的计算工具的进展，如阶梯采样（SS）和热力学积分方案，使贝叶斯模型证据的有效计算成为可能。本文将DIC的能力（即选择真实模型的能力）和速度（即实现给定精度的CPU时间）与使用SS计算的模型证据进行了比较。考虑了三种重要的模型类别：线性回归模型，混合模型和流行病学中广泛使用的区室模型。虽然DIC在应用于线性回归模型时可以正确识别真实模型，但在其他两种情况下，它导致了错误的模型选择。另一方面，在所有考虑的情况下，模型证据导致正确的模型选择。重要的是，也许令人惊讶的是，DIC和模型证据被发现以相似的计算速度运行，这一结果被解析推导的表达式所强化。
While model evidence is considered by Bayesian statisticians as a gold standard for model selection (the ratio in model evidence between two models giving the Bayes factor), its calculation is often viewed as too computationally demanding for many applications. By contrast, the widely used deviance information criterion (DIC), a different measure that balances model accuracy against complexity, is commonly considered a much faster alternative. However, recent advances in computational tools for efficient multi-temperature Markov chain Monte Carlo algorithms, such as steppingstone sampling (SS) and thermodynamic integration schemes, enable efficient calculation of the Bayesian model evidence. This paper compares both the capability (i.e. ability to select the true model) and speed (i.e. CPU time to achieve a given accuracy) of DIC with model evidence calculated using SS. Three important model classes are considered: linear regression models, mixed models and compartmental models widely used in epidemiology. While DIC was found to correctly identify the true model when applied to linear regression models, it led to incorrect model choice in the other two cases. On the other hand, model evidence led to correct model choice in all cases considered. Importantly, and perhaps surprisingly, DIC and model evidence were found to run at similar computational speeds, a result reinforced by analytically derived expressions.
登录
查看更多内容
影响因子：
2.2
作者：
Friel, Nial;Hurn, Merrilee;Wyse, Jason
通讯作者：
Wyse, Jason
影响因子：
2.2
作者：
Friel, N.;McKeone, J. P.;Pettitt, A. N.
通讯作者：
Pettitt, A. N.
影响因子：
2.1
作者：
Knock, Edward S.;O'Neill, Philip D.
通讯作者：
O'Neill, Philip D.
DOI：
10.1073/pnas.0706461104
发表时间：
2007-12-18
影响因子：
11.1
作者：
Cook, Alex R.;Otten, Wilfred;Gilligan, Christopher A.
通讯作者：
Gilligan, Christopher A.
影响因子：
4.4
作者：
Celeux, G.;Forbes, F.;Titterington, D. M.
通讯作者：
Titterington, D. M.