[1]王江荣a,袁维红b,赵睿a,等.基于贝叶斯复合分位数回归的参数估计及应用[J].工业仪表与自动化装置,2016,(05):7-10.
　WANG Jiangronga,YYAN Weihongb,ZHAO Ruia,et al.Parameter estimation and application based on Bayesian composite quantile regression[J].Industrial Instrumentation & Automation,2016,(05):7-10.
点击复制

基于贝叶斯复合分位数回归的参数估计及应用()

《工业仪表与自动化装置》[ISSN:1000-0682/CN:61-1121/TH]

Title:: Parameter estimation and application based on Bayesian composite quantile regression

Author(s):: WANG Jiangronga; YYAN Weihongb; ZHAO Ruia; REN Taimingb; (a. Department of Information Processing and Control Engineering;b.Department of civil engineering, Lanzhou Petrochemical College of Vocational Technology, Lanzhou 730060, China)

Keywords:: Multiple quantile regression; Bayesian regression; least square estimation; polynomial model; settlement prediction

摘要:: 针对传统最小二乘估计易受异常点干扰及稳健性较差的问题，建立了基于复合分位数回归估计的数据拟合预测模型。为了克服复合分位数回归在估计参数时忽视了参数的不确定性，致使估算出的参数精度不够高的缺点，将贝叶斯分析法与复合分位数回归相结合，提高了参数的估算精度。实证分析表明贝叶斯复合分位数回归估计优于复合分位数回归估计，而复合分位数回归估计优于传统最小二乘估计，值得工程技术人员借鉴。

Abstract:: Aiming at the problem that the traditional least squares estimation is vulnerable to outliers and its robustness is poor, the data fitting and forecasting model based on the composite quantile regression estimation is established.In order to overcome the composite quantile regression shortcomings in the estimation of parameters ignore parameter uncertainty, resulting in the disadvantages of estimated parameters and the precision is not very high, By combining the Bias analysis method and the composite quantile regression, the estimation accuracy of the parameters is improved. The empirical analysis shows that the Bayesian composite quantile regression estimation is better than the composite quantile regression estimation, and the composite quantile regression estimation is better than the traditional least squares estimation, and it is worth learning from the engineering and technical personnel.

[1] 张德丰. MATLAB数值分析与仿值案例[M].北京:清华大学出版社,2011.

[2] 施妙根,顾丽珍.科学和工程计算基础[M].北京:清华大学出版社,2002.

[3] Emanuel Paren. Quantile Probability and Statistical Data Modeling[J].Statistical Science,2004,19(4):625-662.

[4] Zou H, Yuan M. Composite quantile regression and the oracle model selection theory[J].The Annals of Statistics, 2008, 36(3):1108–1126.?

[5] 王新宇.分位数回归理论及其在金融风险测量中的应用[M].北京:科学出版社,2010.

[6] 邸俊鹏.分位数回归的贝叶斯估计与应用研究[D].天津:南开大学,2013.

[7] Yu K,Moyeed R A.Bayesian quantile regression. Statistical and Probability Letters,2001,54:437-447.

[8] 刘闯,花向红,赵杰.基于小波去噪的高铁沉降预测模型研究[J].测绘地理信息,2015,40(1):37-40.[9] 韦来生,张伟平.贝叶斯分析[M].合肥:中国科学技术大学出版社,2013.

备注/Memo:: 收稿日期：2016-02-18
基金项目：兰州市科学技术局计划项目（兰财建发[2015]85号）；兰州石化职业技术学院科技资助项目（院发〔2015〕69号）；甘肃省科技厅计划项目“石油化工企业应急演练系统”(1204GKCA004)；甘肃省财政厅专项资金立项资助（甘财教[2013]116号）
作者简介：王江荣（1966），男，甘肃静宁人，硕士，教授，主要从事基路沉降、控制理论与应用方面的研究。

更新日期/Last Update: 1900-01-01