Skip to main content
SpringerLink
Log in

Function-on-Function Partial Quantile Regression

  • Published:
Journal of Agricultural, Biological and Environmental Statistics Aims and scope Submit manuscript

Abstract

A function-on-function linear quantile regression model, where both the response and predictors consist of random curves, is proposed by extending the classical quantile regression setting into the functional data to characterize the entire conditional distribution of functional response. In this paper, a functional partial quantile regression approach, a quantile regression analog of the functional partial least squares regression, is proposed to estimate the function-on-function linear quantile regression model. A partial quantile covariance function is first used to extract the functional partial quantile regression basis functions. The extracted basis functions are then used to obtain the functional partial quantile regression components and estimate the final model. Although the functional random variables belong to an infinite-dimensional space, they are observed in a finite set of discrete-time points in practice. Thus, in our proposal, the functional forms of the discretely observed random variables are first constructed via a finite-dimensional basis function expansion method. The functional partial quantile regression constructed using the functional random variables is approximated via the partial quantile regression constructed using the basis expansion coefficients. The proposed method uses an iterative procedure to extract the partial quantile regression components. A Bayesian information criterion is used to determine the optimum number of retained components. The proposed functional partial quantile regression model allows for more than one functional predictor in the model. However, the true form of the proposed model is unspecified, as the relevant predictors for the model are unknown in practice. Thus, a forward variable selection procedure is used to determine the significant predictors for the proposed model. Moreover, a case-sampling-based bootstrap procedure is used to construct pointwise prediction intervals for the functional response. The predictive performance of the proposed method is evaluated using several Monte Carlo experiments under different data generation processes and error distributions. The finite-sample performance of the proposed method is compared with the functional partial least squares method. Through an empirical data example, air quality data are analyzed to demonstrate the effectiveness of the proposed method.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

References

  • Abbas SA, Xuan Y, Song X (2019) Quantile regression based methods for investigating rainfall trends associated with flooding and drought conditions. Water Resour Manag 33(12):4249–4264

    Article  Google Scholar 

  • Aguilera AM, Escabias M, Preda C, Saporta G (2010) Using basis expansions for estimating functional PLS regression applications with chemometric data. Chemomet Intell Lab Syst 104:289–305

    Article  Google Scholar 

  • Aguilera-Morillo MC, Aguilera AM (2019) Multi-class classiffication of biomechanical data. Stat Modell 20(6):592–616

    Article  MATH  Google Scholar 

  • Antoch J, Prchal L, Rosa MRD, Sarda P (2010) Electricity consumption prediction with functional linear regression using spline estimators. J Appl Stat 37(12):2027–2041

    Article  MathSciNet  MATH  Google Scholar 

  • Beyaztas U, Shang HL (2020) On function-on-function regression: partial least squares approach. Environ Ecol Stat 27(1):95–114

    Article  Google Scholar 

  • Beyaztas U, Shang HL (2021a) A partial least squares approach for function-on-function interaction regression. Comput Stat 36(2):911–939

    Article  MathSciNet  MATH  Google Scholar 

  • Beyaztas U, Shang HL (2021b) A comparison of parameter estimation in function-on-function regression. Communications in Statistics - Simulation and Computation, in press

  • Briollais L, Durrieu G (2014) Application of quantile regression to recent genetic and -omic studies. Human Genet 133(8):951–966

    Article  Google Scholar 

  • Cao C, Shi JQ, Lee Y (2018) Robust functional regression model for marginal mean and subject-specific inferences. Stat Methods Med Res 27(11):3236–3254

    Article  MathSciNet  Google Scholar 

  • Cardot H, Crambes C, Sarda P (2005) Quantile regression when the covariates are functions. J Nonparamet Stat 17(7):841–856

    Article  MathSciNet  MATH  Google Scholar 

  • Cardot H, Crambes C, Sarda P (2007) Ozone pollution forecasting using conditional mean and conditional quantiles with functional covariates. In: Hardle W, Mori Y, Vieu P (eds) Statistical Methods for Biostatistics and Related Fields. Springer, Berlin, pp 221–243

  • Chaouch M, Bouchentouf AA, Traore A, Rabhi A (2020) Single functional index quantile regression under general dependence structure. J Nonparamet Stat 32(3):725–755

    Article  MathSciNet  MATH  Google Scholar 

  • Chen K, Müller H-G (2012) Conditional quantile analysis when covariates are functions, with application to growth data. J Royal Stat Soc Series B 74(1):67–89

    Article  MathSciNet  MATH  Google Scholar 

  • Chiou J-M, Yang Y-F, Chen Y-T (2016) Multivariate functional linear regression and prediction. J Multivar Anal 146:301–312

    Article  MathSciNet  MATH  Google Scholar 

  • Cuevas A (2014) A partial overview of the theory of statistics with functional data. J Stat Plan Inf 147:1–23

    Article  MathSciNet  MATH  Google Scholar 

  • Delaigle A, Hall P (2012) Methodology and theory for partial least squares applied to functional data. The Ann Stat 40(1):322–352

    Article  MathSciNet  MATH  Google Scholar 

  • Dodge Y, Whittaker J (2009) Partial quantile regression. Metrika 70(1):35–57

    Article  MathSciNet  MATH  Google Scholar 

  • Eilers PHC, Roder E, Savelkoul HFJ, van Wijk RG (2012) Quantile regression for the statistical analysis of immunological data with many non-detects. BMC Immunol 13:37

    Article  Google Scholar 

  • Febrero-Bande M, Galeano P, Gonzalez-Manteiga W (2017) Functional principal component regression and functional partial least-squares regression: an overview and a comparative study. Int Stat Rev 85(1):61–83

    Article  MathSciNet  Google Scholar 

  • Ferraty F, Rabhi A, Vieu P (2005) Conditional quantiles for dependent functional data with application to the climatic El Nino phenomenon. Sankhya The Indian J Stat 67(2):378–398

    MathSciNet  MATH  Google Scholar 

  • Ferraty F, Vieu P (2006) Nonparametric Functional Data Analysis. Springer, New York

    MATH  Google Scholar 

  • Greven S, Scheipl F (2017) A general framework for functional regression modelling. Stat Model 17(1–2):1–35

    Article  MathSciNet  MATH  Google Scholar 

  • Hall P, Hosseini-Nasab M (2006) On properties of functional principal components analysis. J Royal Stat Soc Series B 68(1):109–126

    Article  MathSciNet  MATH  Google Scholar 

  • Horvath L, Kokoszka P (2012) Inference for Functional Data with Applications. Springer, New York

    Book  MATH  Google Scholar 

  • Hullait H, Leslie DS, Pavlidis NG, King S (2021) Robust function-on-function regression. Technometrics (in press)

  • Ivanescu AE, Staicu A-M, Scheipl F, Greven S (2015) Penalized function-on-function regression. Comput Stati 30(2):539–568

    Article  MathSciNet  MATH  Google Scholar 

  • Jacques J, Preda C (2014) Model-based clustering for multivariate functional data. Comput Stat Data Anal 71:92–106

    Article  MathSciNet  MATH  Google Scholar 

  • Kato K (2012) Estimation in functional linear quantile regression. The Ann Stat 40(6):3108–3136

    Article  MathSciNet  MATH  Google Scholar 

  • Kim MO (2007) Quantile regression with varying coefficients. The Ann Stat 35(1):92–108

    Article  MathSciNet  MATH  Google Scholar 

  • Koenker R (2005) Quantile Regression. Cambridge University Press, New York

    Book  MATH  Google Scholar 

  • Koenker R (2020) quantreg: quantile regression. R package version 5.67. https://CRAN.R-project.org/package=quantreg

  • Koenker R, Bassett-Jr G (1978) Regression quantiles. Econometrica 46(1):33–50

    Article  MathSciNet  MATH  Google Scholar 

  • Lara S, Tim B, Sindana I, Paige S, Rupa B, Tarik B (2019) A quantile regression approach to examine fine particles, term low birth weight, and racial/ethnic disparities. Environ Epidemiol 3(4):060

    Google Scholar 

  • Lee ER, Noh H, Park BU (2014) Model selection via Bayesian information criterion for quantile regression models. J Am Stat Assoc Theory Methods 109(505):216–229

    Article  MathSciNet  MATH  Google Scholar 

  • Lehn F, Bahrs E (2018) Quantile regressionof german standard farmland values: Do the impacts of determinants vary across the conditional distribution? J Agricul Appl Econ 50(4):674–683

    Google Scholar 

  • Liu Y, Li M, Morris JS (2020) Function-on-scalar quantile regression with application to mass spectrometry proteomics data. The Ann Appl Stat 114(2):521–541

    MathSciNet  MATH  Google Scholar 

  • Luo R, Qi X (2018) FRegSigCom: functional Regression using Signal Compression Approach. R package version 0.3.0. https://CRAN.R-project.org/package=FRegSigCom

  • Luo R, Qi X (2019) Interaction model and model selection for function-on-function regression. J Comput Graph Stat 28(2):309–322

    Article  MathSciNet  Google Scholar 

  • Ma H, Li T, Zhu H, Zhu Z (2019) Quantile regression for functional partially linear model in ultra-high dimensions. Comput Stat Data Anal 129:135–147

    Article  MathSciNet  MATH  Google Scholar 

  • Magzamen S, Amato MS, Imm P, Havlena JA, Coons MJ, Anderson HA, Kanarek MS, Moore CF (2015) Quantile regression in environmental health: early life lead exposureand end-of-grade exams. Environ Res 137:108–119

    Article  Google Scholar 

  • Matsui H (2020) Quadratic regression for functional response models. Econ Stat 13:125–136

    MathSciNet  Google Scholar 

  • Matsui H, Kawano S, Konishi S (2009) Regularized functional regression modeling for functional response and predictors. J Math-for-Ind 1(A3):17–25

    MathSciNet  MATH  Google Scholar 

  • Preda C, Saporta G (2005) PLS regression on a stochastic process. Comput Stat Data Anal 48(1):149–158

    Article  MathSciNet  MATH  Google Scholar 

  • Preda C, Schiltz J (2011) Functional PLS regression with functional response: the basis expansion approach. In: Proceedings of the 14th Applied Stochastic Models and Data Analysis Conference. Universita di Roma La Spienza 1126–1133

  • Ramsay JO, Dalzell CJ (1991) Some tools for functional data analysis. J Royal Stat Soc Series B 53(3):539–572

    MathSciNet  MATH  Google Scholar 

  • Ramsay JO, Silverman BW (2006) Functional Data Analysis, 2nd edn. Springer, New York

    MATH  Google Scholar 

  • Reiss PT, Odgen RT (2007) Functional principal component regression and functional partial least squares. J Am Stat Assoc Theory Methods 102(479):984–996

    Article  MathSciNet  MATH  Google Scholar 

  • Sang P, Cao J (2020) Functional single-index quantile regression models. Stat Comput 30(4):771–781

    Article  MathSciNet  MATH  Google Scholar 

  • Schwarz G (1987) Estimating the dimension of a model. The Ann Stat 6(2):461–464

    MathSciNet  MATH  Google Scholar 

  • Sun Y, Wang Q (2020) Function-on-function quadratic regression models. Comput Stat Data Anal 142:106814

    Article  MathSciNet  MATH  Google Scholar 

  • Tang Q, Cheng L (2014) Partial functional linear quantile regression. Sci China Math 57(12):2589–2608

    Article  MathSciNet  MATH  Google Scholar 

  • Valderrama MJ, Ocana FA, Aguilera AM, Ocana-Peinado FM (2010) Forecasting pollen concentration by a two-step functional model. Biometrics 66(2):578–585

    Article  MathSciNet  MATH  Google Scholar 

  • Vasseur SP, Aznarte JL (2021) Comparing quantile regression methods for probabilistic forecasting of \(NO_2\) pollution levels. Sci China Math 11:11592

    Google Scholar 

  • Vito SD, Massera E, Piga M, Martinotto L, Francia GD (2008) On field calibration of an electronic nose for benzene estimation in an urban pollution monitoring scenario. Sens Actuat B Chem 129(2):750–757

    Article  Google Scholar 

  • Wang HJ, Zhu Z, Zhou J (2009) Quantile regression in partially linear varying coefficient models. The Ann Stat 37(6):3841–3866

    MathSciNet  MATH  Google Scholar 

  • Wang Y, Kong L, Jiang B, Zhou X, Yu S, Zhang L, Heo G (2019) Wavelet-based LASSO in functional linear quantile regression. J Stat Comput Simul 89(6):1111–1130

    Article  MathSciNet  MATH  Google Scholar 

  • Yang H, Baladandayuthapani V, Rao AUK, Morris JS (2020) Quantile function on scalar regression analysis for distributional data. J Am Stat Assoc Appl Case Stud 115(529):90–106

    Article  MathSciNet  MATH  Google Scholar 

  • Yao F, Müller H-G, Wang JL (2005) Functional linear regression analysis for longitudinal data. The Ann Stat 33(6):2873–2903

    Article  MathSciNet  MATH  Google Scholar 

  • Yao F, Sue-Chee S, Wang F (2017) Regularized partially functional quantile regression. J Multivar Anal 156:39–56

    Article  MathSciNet  MATH  Google Scholar 

  • Yu D, Kong L, Mizera I (2016) Partial functional linear quantile regression for neuroimaging data analysis. Neurocomputing 195:74–87

    Article  Google Scholar 

  • Yu D, Zhang L, Mizera I, Jiang B, Kong L (2019) Sparse wavelet estimation in quantile regression with multiple functional predictors. Comput Stat Data Anal 136:12–29

    Article  MathSciNet  MATH  Google Scholar 

Download references

Acknowledgements

We thank editor-in-chief, AE, and two reviewers for their constructive comments, which have helped us produce a much-improved paper. This work was supported by The Scientific and Technological Research Council of Turkey (TUBITAK) (grant no: 120F270).

Author information

Authors and Affiliations

  1. Department of Statistics, Marmara University, Istanbul, Turkey

    Ufuk Beyaztas

  2. Department of Actuarial Studies and Business Analytics, Macquarie University, Sydney, Australia

    Han Lin Shang

  3. Department of Statistics, Dokuz Eylul University, Izmir, Turkey

    Aylin Alin

Authors
  1. Ufuk Beyaztas
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Han Lin Shang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Aylin Alin
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ufuk Beyaztas.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Beyaztas, U., Shang, H.L. & Alin, A. Function-on-Function Partial Quantile Regression. JABES 27, 149–174 (2022). https://doi.org/10.1007/s13253-021-00477-9

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13253-021-00477-9

Keywords

Search

Navigation