贝叶斯组合分位数回归在单指标模型中的应用。

Bayesian composite quantile regression for the single-index model.

机构信息

School of Mathematics, Jilin University, Changchun, China.

School of Mathematics and Statistics, Changchun University of Technology, Changchun, China.

出版信息

PLoS One. 2023 May 10;18(5):e0285277. doi: 10.1371/journal.pone.0285277. eCollection 2023.

DOI:10.1371/journal.pone.0285277

PMID:37163496

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC10171657/

Abstract

By using a Gaussian process prior and a location-scale mixture representation of the asymmetric Laplace distribution, we develop a Bayesian analysis for the composite quantile single-index regression model. The posterior distributions for the unknown parameters are derived, and the Markov chain Monte Carlo sampling algorithms are also given. The proposed method is illustrated by three simulation examples and a real dataset.

摘要

我们使用高斯过程先验和非对称拉普拉斯分布的位置-尺度混合表示，为组合分位数单指标回归模型开发了一种贝叶斯分析。推导出了未知参数的后验分布，并给出了马尔可夫链蒙特卡罗抽样算法。通过三个模拟示例和一个真实数据集说明了所提出的方法。