Local Linear Functional Regression Based on Weighted Distance-based Regression

  • Eva Boj
  • Pedro Delicado
  • Josep Fortiana
Part of the Contributions to Statistics book series (CONTRIB.STAT.)

We consider the problem of nonparametrically predicting a scalar response variable yfrom a functional predictor . We have nobservations ( i yi). We assign a weight wi= K(d(   i)h) to each i, where dis a semimetric, Kis a kernel function and his the bandwidth. Then we fit a Weighted (Linear) Distance-Based Regression, where the weights are as above and the distances are given by a possibly difierent semi-metric.


Weighted Little Square Weighted Version Mean Square Prediction Error Local Linear Regression Variable Bandwidth 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Baíllo, A. and Grané, A.: Local linear regression for functional predictor and scalar response, Univ. Carlos III de Madrid, Statistics and Econometric Series, 07-61 (2007).Google Scholar
  2. [2]
    Barrientos-Marin, Jorge .: Some Practical Problems of Recent Nonparametric Pro-cedures: Testing, Estimation, and Application. Univ. de Alicante (2007).Google Scholar
  3. [3]
    Berlinet,A.,Elamine, A. and Mas, A.: Local linear regres-sionforfunctionaldata",ArXive-prints.0710.5218,710, http://adsabs.harvard.edu/abs/2007arXiv0710.5218B (2007).
  4. [4]
    E. Boj and Claramunt, M. M. and J. Fortiana.: Selection of Predictors in Distance-Based Regression. Comm. in Statistics. Simulation and Computation. 36, 87-98 (2007).MATHCrossRefGoogle Scholar
  5. [5]
    Boj, E. and Fortiana, J.: Weighted Distance-Based Regression, Unpublished (2007).Google Scholar
  6. [6]
    Borg, Ingwer and Groenen, Patrick .: Modern Multidimensional Scaling: Theory and Applications (2nd ed), Springer-Verlag, New York (2005).MATHGoogle Scholar
  7. [7]
    Cuadras, C. M. and Arenas, C.: A distance based regression model for prediction with mixed data. Comm. in Statistics A. Theory and Methods, 19, 2261-2279 (1990).CrossRefMathSciNetGoogle Scholar
  8. [8]
    Cuadras Carles M. and Josep Fortiana.: Distance-Based Multivariate Two Sample Tests IMUB. Institut de Matemàtica de la Universitat de Barcelona. 334 (2003).Google Scholar
  9. [9]
    Cuadras, C. M.: Distance Analysis in discrimination and classi cation using both continuous and categorical variables. dodge:1989, 459-473 (1989).Google Scholar
  10. [10]
    Cuadras, C. M., Arenas, C. and Fortiana, J.: Some computational aspects of a Distance-Based model for Prediction. Comm. in Statistics. Simulation and Com-putation 25, 593-609 (1996).MATHCrossRefGoogle Scholar
  11. [20]
    Ferraty F. and Vieu P.: Nonparametric modelling for functional data. Springer-Verlag, New York. (2006).Google Scholar
  12. [12]
    Ferraty, F., Mas, A. and Vieu, P.: Nonparametric regression on functional data: Inference and practical aspects. Australian and New Zeland J. Stats. 49 (3), 267-286 (2007).MATHCrossRefMathSciNetGoogle Scholar
  13. [13]
    Muñoz-Maldonado, Y., Staniswalis, J.G. and Irwin, L.N. and Byers, D.: A similarity analysis of curves. Canadian Journal of Statistics. 30, 373-381 (2002).MATHCrossRefGoogle Scholar
  14. [14]
    Ramsay, J. and Silverman, B.: Functional Data Analysis (Second Edition) Spinger-Verlag, New York. (2005).Google Scholar

Copyright information

© Physica-Verlag Heidelberg 2008

Authors and Affiliations

  • Eva Boj
    • 1
  • Pedro Delicado
    • 2
  • Josep Fortiana
    • 1
  1. 1.Universitat de BarcelonaSpain
  2. 2.Universitat Politècnica de CatalunyaSpain

Personalised recommendations