基于核函数方法的逐段线性Tobit回归模型估计

doi:10.6040/j.issn.1671-9352.0.2019.865

《山东大学学报(理学版)》 ›› 2020, Vol. 55 ›› Issue (6): 1-9.doi: 10.6040/j.issn.1671-9352.0.2019.865

• •

基于核函数方法的逐段线性Tobit回归模型估计

王小刚,李冰

北方民族大学数学与信息科学学院, 宁夏银川 750021

发布日期:2020-06-01
作者简介:王小刚(1980— ),男,博士,副教授,研究方向为变点理论. E-mail:wxg@nun.edu.cn
基金资助:
国家社会科学基金资助项目(17BTJ033)

Piecewise linear Tobit regression model estimation based on kernel function method

WANG Xiao-gang, LI Bing

School of Mathematics and Information Science, North Minzu University, Yinchuan 750021, Ningxia, China

Published:2020-06-01

摘要/Abstract

摘要： 在变点估计模型中,常用的格点搜索法存在变点估计繁琐和实际意义不强的缺陷,线性化技术得到的变点估计无法证明估计的大样本性质。为克服这些缺陷,在逐段线性Tobit回归模型中利用核函数方法解决了目标函数不可导问题,得到了变点位置估计和参数估计,证明了估计的大样本性质,并利用蒙特卡洛模拟验证了估计效果的有效性和稳健性。针对家庭年金融资产数据进行的实证分析表明,家庭金融资产会受到受教育水平的正向影响,受教育水平在本科前后存在变点。

关键词: 变点, 逐段线性, Tobit回归模型, 核函数

Abstract: In the change point estimation model, the common grid search method has the disadvantages of cumbersome calculation and unreal meaning, and the linearization technique cannot prove the large sample properties. In order to overcome these shortcomings, the kernel function method is proposed in the piecewise linear Tobit regression model to solve the problem of non-differentiable of the objective function, the change point and parameter estimation are obtained, the asymptotic properties are proved, and the validity and robustness of the estimation are verified by Monte Carlo simulation. The empirical analysis of the family annual financial asset data shows that family financial assets would be positively affected by the level of education, and the educational level would change before and after the undergraduate level.

Key words: change point, piecewise linear, Tobit regression model, kernel function

中图分类号:

O212.2

王小刚,李冰. 基于核函数方法的逐段线性Tobit回归模型估计[J]. 《山东大学学报(理学版)》, 2020, 55(6): 1-9.

WANG Xiao-gang, LI Bing. Piecewise linear Tobit regression model estimation based on kernel function method[J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2020, 55(6): 1-9.

参考文献

[1] TOBIN J. Estimation of relationships for limited dependent variables[J]. Econometrica,1958, 26(1):24-36.
[2] AMEMIYA T. Tobit models: a survey[J]. Journal of Econometrics,1984, 24(1):3-61.
[3] PERRON P. Dealing with structural breaks[EB/OL].(2005-04-20)[2019-11-03]. http://people.bu.edu/perron/papers/dealing.pdf.
[4] BAI Jushan. Common breaks in means and variances for panel data[J]. Journal of Econometrics, 2010, 157(1):78-92.
[5] LEE S, SEO M H, SHIN Y. The lasso for high dimensional regression with a possible change point[J]. Journal of Royal Statistics Society B, 2016, 78(1):193-210.
[6] BAI Jushan. Least squares estimation of a shift in linear processes[J]. Journal of Time Series Analysis, 1994, 15(5):453-472.
[7] WANG Zhanfeng, WU Yaohua, ZHAO Lincheng. Change-point estimation for censored regression model[J]. Science in China Series A: Mathematics, 2007, 50(1):63-72.
[8] DANGE G A. Piecewise growth mixture Tobit models: application to AIDS studies[J]. Journal of Biopharmaceutical Statistics, 2015, 25(6):1339-1352.
[9] TANG X Y, MILLER M I, YOUNES L. Biomarker change-point estimation with right censoring in longitudinal studies[J]. Annals of Applied Statistics, 2017, 11(3):1738-1762.
[10] MUGGEO V M R. Estimating regression models with unknown break-points[J]. Statistics in Medicine, 2003, 22(19):3055-3071.
[11] LI C X, WEI Y, CHAPPEL R, et al. Bent line quantile regression with application to an allometric study of land mammals speed and mass[J]. Biometrics, 2011, 67(1):242-249.
[12] LERMAN P M. Fitting segmented regression models by grid search[J]. Journal of the Royal Statistical Society C, 1980, 29(1):77-84.
[13] HOROWITZ J L. A smoothed maximum score estimator for the binary response model[J]. Econometrica, 1992, 60(3):505-531.
[14] MIAN A, SUFI A. House price, home equity-based borrowing, and the US household leverage crisis[J]. The American Eonomics Review, 2011, 101(5):2132-2256.
[15] 谢绵陛. 家庭资产负债的决定因素:基于多变量Tobit方程系统方法[J]. 中央财经大学学报,2018(10):71-81. XIE Mianbi. Determinants of household assets and debets: an approach based on multivariable Tobit system[J]. Journal of Central University of Finance and Economics, 2018(10):71-81.
[16] BROWN S, TAYLOR K. Household debt and financial assets: evidence from Germany, Great Britain and the USA[J]. Journal of the Royal Statistical Society A, 2008, 171(3):615-643.
[17] 李实,魏众,古斯塔夫森. 中国城镇居民的财产分配[J]. 经济研究,2000(3):16-23,79. LI Shi, WEI Zhong, GUSTAFSSON B. Distribution of wealth among urban and township households in China[J]. Economic Research Journal, 2000(3):16-23, 79.
[18] HE Xuming, SHAO Qiman. A general bahadur representation of M-estimators and its application to linear regression[J]. The Annals of Statistics, 1996, 24(6):2608-2630.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于核函数方法的逐段线性Tobit回归模型估计

Piecewise linear Tobit regression model estimation based on kernel function method

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

多维度评价

本文评价

推荐阅读 0

[1]	唐益明,张征,芦启明. 分段二次方转换函数驱动的高斯核模糊C均值聚类[J]. 《山东大学学报(理学版)》, 2020, 55(3): 107-112.
[2]	梁小林,郭敏,李静. 更新几何过程的参数估计[J]. 山东大学学报（理学版）, 2017, 52(8): 53-57.
[3]	刘飚1,2,陈春萍3,封化民1,3,李洋3. 基于Fisher准则的SVM参数选择算法[J]. J4, 2012, 47(7): 50-54.
[4]	王小刚1,2, 王黎明1,3*. 一类面板模型中部分结构变点的检测和估计[J]. J4, 2012, 47(7): 91-99.
[5]	陈月姣,张明望*. 单调线性互补问题基于核函数的满-Newton步不可行内点算法[J]. J4, 2012, 47(10): 81-88.