Functional Partial Linear Regression with Autoregressive Errors

Abstract

This paper investigates a functional partial linear model with autoregressive errors, where the relationship between functional predictor and the scalar response is linear, while the scalar predictor is nonparametric. We first approximate the functional regression parameter and nonparametric function by two given B-spline basis, respectively. Then, we estimate the spline coefficients by a weighted least square method. In the presented paper, we derive the theoretical properties including the convergence rate of the functional regression parameter and the nonparametric function estimate for the scalar predictor. Furthermore, we illustrate the performance of the proposed method by simulation studies and one real data analysis.

References

[1] Aitsaïdi A, Ferraty F, Kassa R, Vieu P. Cross-validated estimations in the single-functional index model Statisitics, 2008, 42(6): 475-494

[2] Aneiros A. Quintela, asymptotic properties in partial linear models under dependence TEST, 2001, 10: 333-355.

[3] Bongiorno EG, Salinelli E, Goia A, Vieu P Contributions in Infinite-dimensional Statistics and Related Topics, 2014 Bologna Societ editrice Esculapio

[4] Brockwell PJ, Davis RA Time Series: Theory and Methods, 1991 New York Springer-Verlag.

[5] Cardot H, Ferraty F, Sarda P. Functional linear model Stat. Probab. Lett., 1999, 45: 11-22.

[6] Cardot H, Ferraty F, Sarda P. Spline estimators for the functional linear model Stat. Sin., 2003, 13: 571-591

[7] Chen H. Polynomial splines and nonparametric regression J. Nonparametric Stat., 1991, 1: 143-156.

[8] Chen KH, Lei J. Localized functional principal component analysis J. Am. Stat. Assoc., 2015, 110: 1266-1275.

[9] Cui X, Lin H, Lian H. Partially functional linear regression in reproducing kernel Hilbert spaces Comput. Stat. Data Anal., 2020, 150: 106978.

[10] Dabo-Niang S, Guillas S. Functional semiparametric partially linear model with autoregressive errors J. Multivar. Anal., 2010, 101: 307-315.

[11] De Boor C A Practical Guide to Splines, 2001 New York Springer

[12] Devore RA, Lorentz GG Constructive Approximation, 1993 Berlin Springer-Verlag.

[13] Du J, Sun X, Cao R, Zhang Zhongzhan. Statistical inference for partially linear additive spatial autoregressive models Spatial Stat., 2018, 25: 52-67.

[14] Du J, Zhang Z, Xu D. Estimation for the censored partially linear quantile regression models Commun. Stat. Simul. Comput., 2018, 8: 2393-2408.

[15] Ferraty F, Mas A, Vieu P. Nonparametric regression on functional data: inference and practical aspects Aust. N. Z. J. Stat., 2007, 49: 267-286.

[16] Ferraty F, Vieu P Nonparametric Functional Data Analysis: Theory and Practice, 2006 New York Springer

[17] Hall P, Horowitz J. Methodology and convergence rates for functional linear regression Ann. Stat., 2007, 53: 70-91

[18] He G, Müller HG, Wang JL. Functional canonical analysis for square integrable stochastic processes J. Multivar. Anal., 2003, 85: 54-77.

[19] HorváthL Kokoszka P Inference for Functional Data with Applications, 2012 New York Springer.

[20] Huang J, Shen H. Functional coefficient regression models for non-linear time series: a polynomial spline approach Scand. J. Stat., 2004, 31: 515-534.

[21] Judge George G The Theory and Practice of Econometrics, 1985 2nd ed Wiley

[22] Lian H. Functional partial linear model J. Nonparametric Stat., 2011, 23(1–2): 115-128.

[23] Müller HG, Yao F. Functional additive models J. Am. Stat. Assoc., 2008, 103: 426-437.

[24] Müller HG, Yao F. Additive modeling of functional gradients Biometrika, 2010, 97: 791-806.

[25] Newey WK. Convergence rates and asymptotic normality for series estimators J. Econometrics, 1997, 79: 147-168.

[26] Ramsay JO, Silverman BW Functional Data Analysis, 2005 2 New York Springer.

[27] Shin H. Partial functional linear regression J. Stat. Plann. Inference, 2009, 139: 3405-3418.

[28] Shi P, Li G. On the rate of convergence of “minimum L 1 \documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$ L_1 $$\end{document}-norm” estimates in a partly linear model Commun. Satistics Theory Methods, 1994, 23: 175-196.

[29] Stone CJ. Additive regression and other nonparametric models Ann. Stat., 1985, 13: 689-705.

[30] Wang GC, Feng XN, Chen M. Functional partial linear single-index model Sacndinavian J. Stat., 2016, 43: 261-274

[31] Wang GC, Su Y, Shu LJ. One-day-ahead daily power forecasting of photovoltaic systems based on partial functional linear regression models Renew. Energy, 2016, 96: 469-478.

[32] Wang, M., Shu, M.L., Zhou, J.J., Wu, S.X.: Least square estimation for multiple functional linear model with autoregressive errors, Acta Mathematica Application Sinica (Enlish Series), manuscript

[33] Wise J. The autocorrelation function and the spectral density function Biometrika, 1955, 42: 151-159.

[34] Xiao P, Wang GC. Partial functional linear regression with autoregreesive errors Communications in Statistics-Theory and Methods, 2022, 51: 4515-4536.

[35] Yao F, Müller HG, Wang JL. Functional data analysis for sparse longitudinal data J. Am. Stat. Assoc., 2005, 100: 577-590.

[36] Yao F, Müller HG. Functional quadratic regression Biometrika, 2010, 97: 49-64.

[37] Yu P, Du J, Zhang Z. Varying-coefficient partially functional linear quantile regression models J. Korean Stat. Soc., 2017, 46: 462-475.

[38] Zhou J, Chen M. Spline estimators for semi-functional linear model Statist. Probab. Lett., 2012, 82: 505-513.

[39] Zhou J, Chen Z, Peng Q. Polynomial spline estimation for partial functional linear regression models Comput. Stats, 2016, 31(3): 1107-1129.

Funding

Natural science of Guangdong province(2020A1515010821)

the Fundamental Research Funds for the Center University(12619624)

RIGHTS & PERMISSIONS

School of Mathematical Sciences, University of Science and Technology of China and Springer-Verlag GmbH Germany, part of Springer Nature