Testing for error correlation in partially functional linear regression models

被引：4

作者：

Li, Qian ^{[1
]}

Tan, Xiangyong ^{[1
]}

Wang, Liming ^{[1
]}

机构：

[1] Shanghai Univ Finance & Econ, Sch Stat & Management, 777 Guoding Rd, Shanghai 200433, Peoples R China

来源：

COMMUNICATIONS IN STATISTICS-THEORY AND METHODS | 2021年 / 50卷 / 03期

关键词：

Series correlation test; functional data analysis; empirical likelihood; SERIAL-CORRELATION; EMPIRICAL LIKELIHOOD;

D O I：

10.1080/03610926.2019.1642492

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

This paper investigates the series correlation test for the partially functional linear regression model (PFLRM). PFLRM relates a scalar response to the predictor variable that is composed of multivariate vectors and random functions. We propose two test statistics for series correlation in PFLRM and derive their asymptotic distributions under the null hypothesis. Numerical studies with finite sample size reveal that the proposed statistics have good performances. Finally, we explore the application of the tests on the electricity consumption data which shows that our test statistics are effective and stable.

引用

页码：747 / 761

页数：15

共 27 条

[1]

Box GEP, 1970, Time Series Analysis: Forecasting and Control, DOI [10.1080/01621459.1970.10481180, DOI 10.1080/01621459.1970.10481180]

[2] TESTING FOR AUTOCORRELATION IN DYNAMIC LINEAR-MODELS [J].