Skip to content

Research at St Andrews

Penalized nonparametric scalar-on-function regression via principal coordinates

Research output: Contribution to journalArticle

Standard

Penalized nonparametric scalar-on-function regression via principal coordinates. / Reiss, Philip T.; Miller, David L.; Wu, Pei Shien; Hua, Wen Yu.

In: Journal of Computational and Graphical Statistics, Vol. 26, No. 3, 2017, p. 569-587.

Research output: Contribution to journalArticle

Harvard

Reiss, PT, Miller, DL, Wu, PS & Hua, WY 2017, 'Penalized nonparametric scalar-on-function regression via principal coordinates' Journal of Computational and Graphical Statistics, vol. 26, no. 3, pp. 569-587. https://doi.org/10.1080/10618600.2016.1217227

APA

Reiss, P. T., Miller, D. L., Wu, P. S., & Hua, W. Y. (2017). Penalized nonparametric scalar-on-function regression via principal coordinates. Journal of Computational and Graphical Statistics, 26(3), 569-587. https://doi.org/10.1080/10618600.2016.1217227

Vancouver

Reiss PT, Miller DL, Wu PS, Hua WY. Penalized nonparametric scalar-on-function regression via principal coordinates. Journal of Computational and Graphical Statistics. 2017;26(3):569-587. https://doi.org/10.1080/10618600.2016.1217227

Author

Reiss, Philip T. ; Miller, David L. ; Wu, Pei Shien ; Hua, Wen Yu. / Penalized nonparametric scalar-on-function regression via principal coordinates. In: Journal of Computational and Graphical Statistics. 2017 ; Vol. 26, No. 3. pp. 569-587.

Bibtex - Download

@article{5acab15d503340f1bc15f8544b868fc0,
title = "Penalized nonparametric scalar-on-function regression via principal coordinates",
abstract = "A number of classical approaches to nonparametric regression have recently been extended to the case of functional predictors. This article introduces a new method of this type, which extends intermediate-rank penalized smoothing to scalar-on-function regression. In the proposed method, which we call principal coordinate ridge regression, one regresses the response on leading principal coordinates defined by a relevant distance among the functional predictors, while applying a ridge penalty. Our publicly available implementation, based on generalized additive modeling software, allows for fast optimal tuning parameter selection and for extensions to multiple functional predictors, exponential family-valued responses, and mixed-effects models. In an application to signature verification data, principal coordinate ridge regression, with dynamic time warping distance used to define the principal coordinates, is shown to outperform a functional generalized linear model. Supplementary materials for this article are available online.",
keywords = "Dynamic time warping, Functional regression, Generalized additive model, Kernel ridge regression, Multidimensional scaling",
author = "Reiss, {Philip T.} and Miller, {David L.} and Wu, {Pei Shien} and Hua, {Wen Yu}",
note = "Philip Reiss, Pei-Shien Wu, and Wen-Yu Hua gratefully acknowledge the support of the U.S. National Institute of Mental Health (grant 1R01MH095836-01A1).",
year = "2017",
doi = "10.1080/10618600.2016.1217227",
language = "English",
volume = "26",
pages = "569--587",
journal = "Journal of Computational and Graphical Statistics",
issn = "1061-8600",
publisher = "American Statistical Association",
number = "3",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - Penalized nonparametric scalar-on-function regression via principal coordinates

AU - Reiss, Philip T.

AU - Miller, David L.

AU - Wu, Pei Shien

AU - Hua, Wen Yu

N1 - Philip Reiss, Pei-Shien Wu, and Wen-Yu Hua gratefully acknowledge the support of the U.S. National Institute of Mental Health (grant 1R01MH095836-01A1).

PY - 2017

Y1 - 2017

N2 - A number of classical approaches to nonparametric regression have recently been extended to the case of functional predictors. This article introduces a new method of this type, which extends intermediate-rank penalized smoothing to scalar-on-function regression. In the proposed method, which we call principal coordinate ridge regression, one regresses the response on leading principal coordinates defined by a relevant distance among the functional predictors, while applying a ridge penalty. Our publicly available implementation, based on generalized additive modeling software, allows for fast optimal tuning parameter selection and for extensions to multiple functional predictors, exponential family-valued responses, and mixed-effects models. In an application to signature verification data, principal coordinate ridge regression, with dynamic time warping distance used to define the principal coordinates, is shown to outperform a functional generalized linear model. Supplementary materials for this article are available online.

AB - A number of classical approaches to nonparametric regression have recently been extended to the case of functional predictors. This article introduces a new method of this type, which extends intermediate-rank penalized smoothing to scalar-on-function regression. In the proposed method, which we call principal coordinate ridge regression, one regresses the response on leading principal coordinates defined by a relevant distance among the functional predictors, while applying a ridge penalty. Our publicly available implementation, based on generalized additive modeling software, allows for fast optimal tuning parameter selection and for extensions to multiple functional predictors, exponential family-valued responses, and mixed-effects models. In an application to signature verification data, principal coordinate ridge regression, with dynamic time warping distance used to define the principal coordinates, is shown to outperform a functional generalized linear model. Supplementary materials for this article are available online.

KW - Dynamic time warping

KW - Functional regression

KW - Generalized additive model

KW - Kernel ridge regression

KW - Multidimensional scaling

UR - http://www.tandfonline.com/doi/full/10.1080/10618600.2016.1217227#supplemental-material-section

U2 - 10.1080/10618600.2016.1217227

DO - 10.1080/10618600.2016.1217227

M3 - Article

VL - 26

SP - 569

EP - 587

JO - Journal of Computational and Graphical Statistics

T2 - Journal of Computational and Graphical Statistics

JF - Journal of Computational and Graphical Statistics

SN - 1061-8600

IS - 3

ER -

Related by author

  1. Density and distribution of western chimpanzees around a bauxite deposit in the Boé Sector, Guinea-Bissau

    Dias, F., Wenceslau, J., Marques, T. A. & Miller, D. L., 13 Sep 2019, In : American Journal of Primatology. Early View, e23047.

    Research output: Contribution to journalComment/debate

  2. From here and now to there and then: Practical recommendations for extrapolating cetacean density surface models to novel conditions

    Bouchet, P. J-F., Miller, D. L., Roberts, J., Mannocci, L., Harris, C. M. & Thomas, L., 4 Sep 2019, 59 p. (CREEM Technical Report; vol. 2019, no. 1)

    Research output: Book/ReportOther report

  3. Understanding the stochastic partial differential equation approach to smoothing

    Miller, D. L., Glennie, R. & Seaton, A. E., 3 Sep 2019, (Accepted/In press) In : Journal of Agricultural, Biological and Environmental Statistics. In press

    Research output: Contribution to journalArticle

  4. Hierarchical generalized additive models in ecology: an introduction with mgcv

    Pedersen, E. J., Miller, D. L., Simpson, G. L. & Ross, N., 27 May 2019, In : PeerJ. 7, 42 p., e6876.

    Research output: Contribution to journalArticle

  5. Distance sampling in R

    Miller, D. L., Rexstad, E., Thomas, L., Marshall, L. & Laake, J. L., 9 May 2019, In : Journal of Statistical Software. 89, 1, 28 p.

    Research output: Contribution to journalArticle

Related by journal

  1. Complex Region Spatial Smoother (CReSS)

    Scott Hayward, L. A. S., MacKenzie, M. L., Donovan, C. R., Walker, C. & Ashe, E., 28 Apr 2014, In : Journal of Computational and Graphical Statistics. 23, 2, p. 340-360

    Research output: Contribution to journalArticle

ID: 250174746