文章基本信息

标题：deconvolveR: A G-Modeling Program for Deconvolution and Empirical Bayes Estimation
本地全文：下载
作者：Balasubramanian Narasimhan ; Bradley Efron
期刊名称：Journal of Statistical Software
印刷版ISSN：1548-7660
电子版ISSN：1548-7660
出版年度：2020
卷号：94
期号：1
页码：1-20
DOI：10.18637/jss.v094.i11
出版社：University of California, Los Angeles
摘要：Empirical Bayes inference assumes an unknown prior density g(θ) has yielded (unobservables) Θ 1 , Θ 2 , ..., Θ N , and each Θ i produces an independent observation X i from p i (X i Θ i ). The marginal density f i (X i ) is a convolution of the prior g and p i . The Bayes deconvolution problem is one of recovering g from the data. Although estimation of g - so called g-modeling - is difficult, the results are more encouraging if the prior g is restricted to lie within a parametric family of distributions. We present a deconvolution approach where g is restricted to be in a parametric exponential family, along with an R package deconvolveR designed for the purpose.
关键词：Bayes deconvolution;g-modeling;empirical Bayes;missing species;R package deconvolveR.
其他关键词：Bayes deconvolution;g-modeling;empirical Bayes;missing species;R package deconvolveR