Testing for linearity in scalar-on-function regression with responses missing at random

被引:0
|
作者
Febrero-Bande, Manuel [1 ]
Galeano, Pedro [2 ,3 ]
Garcia-Portugues, Eduardo [2 ,3 ]
Gonzalez-Manteiga, Wenceslao [1 ]
机构
[1] Univ Santiago Compostela, Dept Stat Math Anal & Optimizat, Rua Lope Gomez Marzoa S-N, Santiago De Compostela 15705, Spain
[2] Univ Carlos III Madrid, Dept Stat, Calle Madrid 126, Getafe 28903, Spain
[3] Univ Carlos III Madrid, Santander Big Data Inst, UC3M, Calle Madrid 126, Getafe 28903, Spain
关键词
Functional linear model; Functional principal components; Goodness-of-fit tests; Marked empirical processes; Missing at random; Wild bootstrap; OF-FIT TESTS; MODEL; CHECKING;
D O I
10.1007/s00180-023-01445-2
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
A goodness-of-fit test for the Functional Linear Model with Scalar Response (FLMSR) with responses Missing at Random (MAR) is proposed in this paper. The test statistic relies on a marked empirical process indexed by the projected functional covariate and its distribution under the null hypothesis is calibrated using a wild bootstrap procedure. The computation and performance of the test rely on having an accurate estimator of the functional slope of the FLMSR when the sample has MAR responses. Three estimation methods based on the Functional Principal Components (FPCs) of the covariate are considered. First, the simplified method estimates the functional slope by simply discarding observations with missing responses. Second, the imputed method estimates the functional slope by imputing the missing responses using the simplified estimator. Third, the inverse probability weighted method incorporates the missing response generation mechanism when imputing. Furthermore, both cross-validation and LASSO regression are used to select the FPCs used by each estimator. Several Monte Carlo experiments are conducted to analyze the behavior of the testing procedure in combination with the functional slope estimators. Results indicate that estimators performing missing-response imputation achieve the highest power. The testing procedure is applied to check for linear dependence between the average number of sunny days per year and the mean curve of daily temperatures at weather stations in Spain.
引用
收藏
页码:3405 / 3429
页数:25
相关论文
共 50 条
  • [1] A comparison of testing methods in scalar-on-function regression
    Tekbudak, Merve Yasemin
    Alfaro-Cordoba, Marcela
    Maity, Arnab
    Staicu, Ana-Maria
    ASTA-ADVANCES IN STATISTICAL ANALYSIS, 2019, 103 (03) : 411 - 436
  • [2] Restricted likelihood ratio tests for linearity in scalar-on-function regression
    McLean, Mathew W.
    Hooker, Giles
    Ruppert, David
    STATISTICS AND COMPUTING, 2015, 25 (05) : 997 - 1008
  • [3] Restricted likelihood ratio tests for linearity in scalar-on-function regression
    Mathew W. McLean
    Giles Hooker
    David Ruppert
    Statistics and Computing, 2015, 25 : 997 - 1008
  • [4] A comparison of testing methods in scalar-on-function regression
    Merve Yasemin Tekbudak
    Marcela Alfaro-Córdoba
    Arnab Maity
    Ana-Maria Staicu
    AStA Advances in Statistical Analysis, 2019, 103 : 411 - 436
  • [5] Methods for Scalar-on-Function Regression
    Reiss, Philip T.
    Goldsmith, Jeff
    Shang, Han Lin
    Ogden, R. Todd
    INTERNATIONAL STATISTICAL REVIEW, 2017, 85 (02) : 228 - 249
  • [6] Scalar-on-function local linear regression and beyond
    Ferraty, F.
    Nagy, S.
    BIOMETRIKA, 2022, 109 (02) : 439 - 455
  • [7] Estimator selection and combination in scalar-on-function regression
    Goldsmith, Jeff
    Scheipl, Fabian
    COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2014, 70 : 362 - 372
  • [8] A robust scalar-on-function logistic regression for classification
    Mutis, Muge
    Beyaztas, Ufuk
    Simsek, Gulhayat Golbasi
    Shang, Han Lin
    COMMUNICATIONS IN STATISTICS-THEORY AND METHODS, 2023, 52 (23) : 8538 - 8554
  • [9] Robust scalar-on-function partial quantile regression
    Beyaztas, Ufuk
    Tez, Mujgan
    Lin Shang, Han
    JOURNAL OF APPLIED STATISTICS, 2024, 51 (07) : 1359 - 1377
  • [10] Selecting the derivative of a functional covariate in scalar-on-function regression
    Hooker, Giles
    Shang, Han Lin
    STATISTICS AND COMPUTING, 2022, 32 (03)