Background: We proposed approximate Bayesian computation with single distribution selection (ABC-SD) for estimating mean and standard deviation from other reported summary statistics. The ABC-SD generates pseudo data from a single parametric distribution thought to be the true distribution of underlying study data. This single distribution is either an educated guess, or it is selected via model selection using posterior probability criterion for testing two or more candidate distributions. Further analysis indicated that when model selection is used, posterior model probabilities are sensitive to the prior distribution(s) for parameter(s) and dependable on the type of reported summary statistics. Method: We propose ABC with Bayesian model averaging (ABC-BMA) methodology to estimate mean and standard deviation based on various sets of other summary statistics reported in published studies. We conduct a Monte Carlo simulation study to compare the new proposed ABC-BMA method with our previous ABC-SD method. Results: In the estimation of standard deviation, ABC-BMA has smaller average relative errors (AREs) than that of ABC-SD for normal, lognormal, beta, and exponential distributions. For Weibull distribution, ARE of ABC-BMA is larger than that of ABC-SD but <0.05 in small sample sizes and moves toward zero as sample size increases. When underlying distribution is highly skewed and available summary statistics are only quartiles and sample size, ABC-BMA is recommended but it should be used with caution. Comparison of mean estimation between ABC-BMA and ABC-SD shows similar patterns of results as for standard deviation estimation. Conclusion: ABC-BMA is easy to implement and it performs even better than our previous ABC-SD method for estimation of mean and standard deviation.
Approximating the Likelihood in Approximate Bayesian Computation
本章将出现在即将出版的近似贝叶斯计算手册(2018)中。支撑近似贝叶斯计算(ABC)的概念和方法框架主要针对可能性具有挑战性或缺失的问题。ABC使用基于模拟的非参数估计汇总统计量的可能性,并假设从模型生成数据在计算上是便宜的。本章回顾了两种估计棘手的可能性的替代方法,目的是减少必要的模型模拟,以产生近似的后验。其中第一个是合成似然(SL)的贝叶斯版本,最初由Wood(2010)开发,它使用多变量正态近似来概括统计似然。使用ABC的参数近似而不是非参数近似,可以减少所需的模型模拟的数量。我们在本章中考虑的第二种似然近似方法是基于经验似然(EL),这是一种非参数技术,涉及在一组矩约束下最大化经验构建的似然。Mengersen et al(2013)修改了EL框架,以便它可以用于形成ABC可以应用的问题的近似后验,即具有棘手可能性的模型。然而,与ABC和贝叶斯SL(BSL)不同,贝叶斯EL(BCel)方法可以在某些情况下完全避免模型模拟。BSL和BCel方法说明了不同复杂性的模型。
Simulation-based Estimation of Mean and Standard Deviation for Meta-analysis via Approximate Bayesian Computation (ABC)
背景资料:当对连续结局进行荟萃分析时,需要估计所选研究的平均值和标准差,以获得平均效应及其置信区间的总体估计值。如果出版物中没有直接报告这些数量,则必须根据其他报告的汇总统计量(如中位数、最小值、最大值和四分位数)估计这些数量。研究方法:我们提出了一种基于模拟的估计方法,使用近似贝叶斯计算(ABC)技术估计平均值和标准差的基础上,在已发表的研究中发现的各种汇总统计。我们进行了一项模拟研究,将提出的ABC方法与Hozo et al.(2005),Bland(2015)和Wan et al.(2014)的现有方法进行比较。结果:在标准差的估计中,我们的ABC方法在偏态或重尾分布中表现最好。随着样本量的增加,平均相对误差(ARE)趋于零。在正态分布中,我们的ABC表现良好。然而,Wan等人的方法是最好的,因为它基于正态分布假设。当分布是偏态或重尾分布时,Wan等人的ARE会随着样本量的增加而远离零。在均值的估计中,我们的ABC方法是最好的,因为ARE收敛到零。结论:ABC是一种灵活的方法,用于估计荟萃分析的研究特定平均值和标准差,特别是在潜在的偏态或重尾分布的情况下。当采用贝叶斯分析时,ABC方法可以使用其他报告的汇总统计量,例如后验均值和95%可信区间。
Minimum Risk Equivariant Estimation of the Parameters of the General Half-Normal Distribution by Means of a Monte Carlo Method to Approximate Conditional Expectations
Model averaging with mixed criteria for estimating high quantiles of extreme values: Application to heavy rainfall
Honam Research Division, Electronics and Telecommunications Research Institute(韩国电子与电信研究院湖南研究部);Department of Statistics, Chonnam National University(全南大学统计系)
Estimating the number of household TV profiles based in customer behaviour using Gaussian mixture model averaging
Hamilton Institute, Maynooth University(马尼特大学哈密尔顿研究所);Department of Mathematics and Statistics, Maynooth University(马尼特大学数学与统计学系);Ulster University(乌斯特大学);British Telecommunications(英国电信)