基于非对称拉普拉斯分布的混合分位数回归参数估计

doi:10.12066/j.issn.1007-2861.2125

上海大学学报(自然科学版) ›› 2021, Vol. 27 ›› Issue (3): 601-610.doi: 10.12066/j.issn.1007-2861.2125

• 研究论文 • 上一篇

基于非对称拉普拉斯分布的混合分位数回归参数估计

张发赶, 何幼桦()

上海大学理学院, 上海 200444

收稿日期:2019-03-13 出版日期:2021-06-30 发布日期:2021-06-27
通讯作者: 何幼桦 E-mail:heyouhua@shu.edu.cn
作者简介:何幼桦(1960—), 男, 副教授, 研究方向为数理统计. E-mail: heyouhua@shu.edu.cn
基金资助:
国家自然科学基金资助项目(11471208)

Estimation of mixed quantile regression parameters based on an asymmetric Laplace distribution

ZHANG Fagan, HE Youhua()

College of Sciences, Shanghai University, Shanghai 200444, China

Received:2019-03-13 Online:2021-06-30 Published:2021-06-27
Contact: HE Youhua E-mail:heyouhua@shu.edu.cn

摘要/Abstract

摘要：

利用非对称拉普拉斯分布提出一种新的混合分位数回归模型. 传统模型仅考虑位置参数, 而所提出模型同时考虑了位置参数和尺度参数, 并利用期望最大化(expectation maximization, EM)算法对模型参数进行估计. 数值分析结果表明, 参数估计的精度在各个分位数上均较为理想, 并且估计精度随着样本量的增加而提高. 最后运用所提出模型及其算法对城市房价数据进行分析.

关键词: 混合分位数回归, 非对称拉普拉斯分布, 期望最大化(expectation maximization, EM)算法

Abstract:

A new mixed quantile regression model is established using an asymmetric Laplace distribution. Traditional models consider only positional parameters, whereas our model considers the regression of both positional and scale parameters. The expectation maximization (EM) algorithm was used to compute the estimated values of the model parameters. Numerical simulation results showed that the proposed parameter estimation was precise in each quantile, and a larger sample offered higher precision. Our model was applied to the analysis of urban house prices.

Key words: mixed quantile regression, asymmetric Laplace distribution, expectation maximization (EM) algorithm

中图分类号:

O212.8

张发赶, 何幼桦. 基于非对称拉普拉斯分布的混合分位数回归参数估计[J]. 上海大学学报(自然科学版), 2021, 27(3): 601-610.

ZHANG Fagan, HE Youhua. Estimation of mixed quantile regression parameters based on an asymmetric Laplace distribution[J]. Journal of Shanghai University（Natural Science Edition）, 2021, 27(3): 601-610.

图/表 7

表1

表2

表3

表4

图1

表5

图2

参考文献 12

[1]	Bassett G, Roger K. Regression quantiles[J]. Econometrica, 1978,46(1):33-50. doi: 10.2307/1913643
[2]	Powell J L. Censored regression quantiles[J]. Journal of Econometrics, 1986,32(1):143-155. doi: 10.1016/0304-4076(86)90016-3
[3]	Thompson M L, Fatti L P, Senaoana E M. Bayesian updating in reference centile charts[J]. Journal of the Royal Statistical Society, 1998,161(1):103-115.
[4]	Yu K, Moyeed R A. Bayesian quantile regression[J]. Statistics and Probability Letters, 2001,54(4):437-447. doi: 10.1016/S0167-7152(01)00124-9
[5]	Taddy M A, Kottas A. A Bayesian nonparametric approach to inference for quantile regression[J]. Journal of Business and Economic Statistics, 2010,28(3):357-369. doi: 10.1198/jbes.2009.07331
[6]	Goldfeld S M, Quandt R E. A Markov model for switching regressions[J]. Journal of Econometrics, 1973,1(1):3-15. doi: 10.1016/0304-4076(73)90002-X
[7]	Yao W X, Wei Y, Yu C. Robust mixture regression using the t-distribution[J]. Computational Statistics and Data Analysis, 2014,71(3):116-127. doi: 10.1016/j.csda.2013.07.019
[8]	Song W X, Yao W X, Xing Y R. Robust mixture regression model fitting by Laplace distribution[J]. Computational Statistics and Data Analysis, 2014,71:128-137. doi: 10.1016/j.csda.2013.06.022
[9]	Park R E. Estimation with heteroscedastic error terms[J]. Econometrica, 1966,34(4):888. doi: 10.2307/1910108
[10]	Wu Q, Yao W X. Mixtures of quantile regressions[J]. Computational Statistics and Data Analysis, 2016,93:162-176. doi: 10.1016/j.csda.2014.04.014
[11]	詹金龙, 张舒宇, 吴刘仓. 基于 Laplace 分布下混合联合位置与尺度模型的参数估计[J]. 应用概率统计, 2017,33(5):487-496.
	Zhan J L, Zhang S Y, Wu L C. Parameters estimation for mixture of joint location and scale models based on the Laplace distribution[J]. Chinese Journal of Applied Probability and Statistics, 2017,33(5):487-496.
[12]	李航. 统计学习方法 [M]. 北京: 清华大学出版社, 2012: 162-165.

基于非对称拉普拉斯分布的混合分位数回归参数估计

Estimation of mixed quantile regression parameters based on an asymmetric Laplace distribution

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 7

参考文献 12

相关文章 2

编辑推荐

Metrics

本文评价

[1]	赵焕丽, 何幼桦. 半参数顺序回归的贝叶斯推断[J]. 上海大学学报(自然科学版), 2021, 27(1): 218-226.
[2]	张世斌, 时寰. 基于动态随机前沿模型的集装箱码头技术效率分析[J]. 上海大学学报(自然科学版), 2018, 24(4): 609-616.