Sage Journals: Discover world-class research

Abstract

A function-on-function regression model with quadratic and interaction effects of the covariates provides a more flexible model. Despite several attempts to estimate the model’s parameters, almost all existing estimation strategies are non-robust against outliers. Outliers in the quadratic and interaction effects may deteriorate the model structure more severely than their effects in the main effect. We propose a robust estimation strategy based on the robust functional principal component decomposition of the function-valued variables and $τ$ -estimator. The performance of the proposed method relies on the truncation parameters in the robust functional principal component decomposition of the function-valued variables. A robust Bayesian information criterion is used to determine the optimum truncation constants. A forward stepwise variable selection procedure is employed to determine relevant main, quadratic, and interaction effects to address a possible model misspecification. The finite-sample performance of the proposed method is investigated via a series of Monte-Carlo experiments. The proposed method’s asymptotic consistency and influence function are also studied in the Supplemental Material, and its empirical performance is further investigated using a U.S. COVID-19 dataset.

Keywords

functional principal component analysis interaction effects main effects quadratic effects τ-estimator

Get full access to this article

View all access options for this article.

References

Agulló

, Croux

, and Aelst

S. V.

(2008). The multivariate least-trimmed squares estimator. Journal of Multivariate Analysis , 99, 311–338.

Bali

J. L.

, Boente

, Tyler

D. E.

, and Wang

J.-L.

(2011). Robust functional principal components: A projection-pursuit approach. The Annals of Statistics , 39, 2852–2882.

Beaton

A. E.

, and Tukey

J. W.

(1974). The fitting of power series, meaning polynomials, illustrated on band-spectroscopic data. Technometrics , 16, 147–185.

Ben

M. G.

, Martinez

, and Yohai

V. J.

(2006). Robust estimation for the multivariate linear model based on a τ scale. Journal of Multivariate Analysis , 97, 1600–1622.

Beyaztas

, and Shang

H. L.

(2019). Forecasting functional time series using weighted likelihood methodology. Journal of Statistical Computation and Simulation , 89, 3046–3060.

Beyaztas

, and Shang

H. L.

(2020). On function-on-function regression: Partial least squares approach. Environmental and Ecological Statistics , 27, 95–114.

Beyaztas

, and Shang

H. L.

(2021). A partial least squares approach for function-on-function interaction regression. Computational Statistics , 36, 911–939.

Beyaztas

, and Shang

H. L.

(2022a). A robust partial least squares approach for function-on-function regression. Brazilian Journal of Probability and Statistics , 36, 199–219.

Beyaztas

, and Shang

H. L.

(2022b). A comparison of parameter estimation in function-on-function regression. Communications in Statistics – Simulation and Computation , 51, 4607–4637.

10.

Bilodeau

, and Duchesne

(2000). Robust estimation of the SUR model. The Canadian Journal of Statistics , 28, 277–288.

11.

Brockhaus

, Rügamer

, and Greven

(2020). Boosting functional regression models with FDboost. Journal of Statistical Software , 94, 1–50.

12.

Cai

, Xue

, and Cao

(2021). Robust penalized M-estimation for function-on-function linear regression. Stat , 10, e390.

13.

Cai

, Xue

, and Cao

(2022). Variable selection for multiple function-on-function linear regression. Statistica Snica , 1032, 1435–1465.

14.

Chiou

J.-M.

, Yang

Y.-F.

, and Chen

Y.-T.

(2016). Multivariate functional linear regression and prediction. Journal of Multivariate Analysis , 146, 301–312.

15.

Croux

, and Ruiz-Gazen

(1996). High breakdown estimators for principal components: the projection-pursuit approach revisited. Journal of Multivariate Analysis , 95, 206–226.

16.

Croux

, Filzmoser

, and Fritz

(2013). Robust sparse principal component analysis. Technometrics , 55, 202–214.

17.

Cuaves

, Febrero

, and Fraiman

(2007). Robust estimation and classification for functional data via projection-based depth notions. Computational Statistics , 22, 481–496.

18.

de Lathuauwer

, de Moor

, and Vandewalle

(2000). A multilinear singular value decomposition. SIAM Journal on Matrix Analysis and Applications , 21, 1253–1278.

19.

Dutta

, and Genton

M. G.

(2017). Depth-weighted robust multivariate regression with application to sparse data. The Canadian Journal of Statistics , 45, 164–184.

20.

Febrero-Bande

, Galeano

, and Gonzalez-Mantelga

(2008). Outlier detection in functional data by depth measures, with application to identify abnormal NO

_{x}

levels. Environmetrics , 19, 331–345.

21.

Greven

, and Scheipl

(2017). A general framework for functional regression modelling. Statistical Modelling , 17, 1–35.

22.

Hössjer

(1992). On the optimality of S-estimators. Statistics & Probability Letters , 14, 413–419.

23.

Hullait

, Leslie

D. S.

, Pavlidis

N. G.

, and King

(2021). Robust function-on-function regression. Technometrics , 63, 396–409.

24.

Ivanescu

A. E.

, Staicu

A.-M.

, Scheipl

, and Greven

(2015). Penalized function-on-function regression. Computational Statistics , 30, 539–568.

25.

Jin

, Sun

, and Du

(2023). Optimal function-on-function regression with interaction between functional predictors. Statistica Sinica , 107–1068.

26.

Kalogridis

, and Aelst

S. V.

(2019). Robust functional regression based on principal components. Journal of Multivariate Analysis , 173, 393–415.

27.

Koenker

, and Portnoy

(1990). M estimation of multivariate regressions. Journal of the American Statistical Association: Theory and Methods , 85, 1060–1068.

28.

Kudraszow

N. L.

, and Moronna

R. A.

(2011). Estimates of MM type for the multivariate linear model. Journal of Multivariate Analysis , 102, 1280–1292.

29.

Luo

, and Qi

(2019). Interaction model and model selection for function-on-function regression. Journal of Computational and Graphical Statistics , 28, 309–322.

30.

Luo

, and Qi

(2022). Restricted function-on-function linear regression model. Biometrics , 78(3), 1031–1044.

31.

Matsui

(2020). Quadratic regression for functional response models. Econometrics and Statistics , 13, 125–136.

32.

Müller

H.-G.

, and Yao

(2008). Functional additive models. Journal of the American Statistical Association: Theory and Methods , 103, 1534–1544.

33.

Pya

, Voinov

, Makarov

, and Voinov

(2016). mvnTest: Goodness of Fit Tests for Multivariate Normality . URL https://CRAN.R-project.org/package=mvnTest. R package version 1.1-0.

34.

Ramsay

J. O.

, and Dalzell

C. J.

(1991). Some tools for functional data analysis. Journal of the Royal Statistical Society, Series B , 53, 539–572.

35.

Rousseeuw

P. J.

, Driessen

K. V.

, Aelst

S. V.

, and Agulló

(2004). Robust multivariate regression. Technometrics , 46, 293–305.

36.

Sun

, and Wang

(2020). Function-on-function quadratic regression models. Computational Statistics & Data Analysis , 142, 106814.

37.

Wang

(2021). Two-sample inference for sparse functional data. Electronic Journal of Statistics , 15, 1395–1423.

38.

Wang

(2014). Linear mixed function-on-function regression models. Biometrics , 70, 794–801.

39.

Wang

, Dong

, Ma

, and Wang

(2022). Estimation and model selection for nonparametric function-on-function regression. Journal of Computational and Graphical Statistics , 31, 835–845.

40.

Wilcox

(2012). Introduction to Robust Estimation and Hypothesis Testing . Elsevier, Waltham, MA.

41.

Yao

, Müller

H.-G.

, and Wang

J.-L.

(2005). Functional linear regression analysis for longitudinal data. The Annals of Statistics , 33, 2873–2903.

42.

Yohai

V. J.

, and Zamar

R. H.

(1988). High breakdown-point estimates of regression by means of the minimization of an efficient scale. Journal of the American Statistical Association: Theory and Methods , 83, 406–413.

43.

Zhou

(2021). Fast implementation of partial least squares for function-on-function regression. Journal of Multivariate Analysis , 185, 104769.

Supplementary Material

Please find the following supplemental material available below.

For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.

For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.

3.69 MB

0.00 MB

Robust function-on-function interaction regression

Abstract

Keywords

Get full access to this article

References

Supplementary Material