Stepwise regression is an alternative to splines for fitting noisy data

Thomas J. Burkholder; Richard L. Lieber

doi:10.1016/0021-9290(95)00044-5

Stepwise regression is an alternative to splines for fitting noisy data

Thomas J. Burkholder, Richard L. Lieber^*

^*Corresponding author for this work

Physical Medicine and Rehabilitation

Research output: Contribution to journal › Article › peer-review

40 Scopus citations

Abstract

In this study, we compared numerical methods that are used to fit noisy data. Comparisons included polynominal regression, stepwise polynomial regression and quintic spline approximation. The advantages and limitations of each method are discussed in terms of curve fit quality, computational speed and ease, and solution compactness, Overall, the spline approximation and stepwise polynomial regression provide the best fits to the data. Stepwise regression provides the added utility of providing a simple, unconstrained function which can be easily implemented in simulation studies.

Original language	English (US)
Pages (from-to)	235-238
Number of pages	4
Journal	Journal of Biomechanics
Volume	29
Issue number	2
DOIs	https://doi.org/10.1016/0021-9290(95)00044-5
State	Published - Feb 1996

Funding

Acknowledgements-This work was supported by the Veterans Administration and NIH grants AR35192 and AR40050. We thank Drs Greg Loren and Scott Shoemaker for helpful discussions.

ASJC Scopus subject areas

Biophysics
Orthopedics and Sports Medicine
Biomedical Engineering
Rehabilitation

Access to Document

10.1016/0021-9290(95)00044-5

Cite this

@article{6fa3088bd44e48dda257940120ad1f5c,

title = "Stepwise regression is an alternative to splines for fitting noisy data",

abstract = "In this study, we compared numerical methods that are used to fit noisy data. Comparisons included polynominal regression, stepwise polynomial regression and quintic spline approximation. The advantages and limitations of each method are discussed in terms of curve fit quality, computational speed and ease, and solution compactness, Overall, the spline approximation and stepwise polynomial regression provide the best fits to the data. Stepwise regression provides the added utility of providing a simple, unconstrained function which can be easily implemented in simulation studies.",

author = "Burkholder, {Thomas J.} and Lieber, {Richard L.}",

note = "Funding Information: Acknowledgements-This work was supported by the Veterans Administration and NIH grants AR35192 and AR40050. We thank Drs Greg Loren and Scott Shoemaker for helpful discussions.",

year = "1996",

month = feb,

doi = "10.1016/0021-9290(95)00044-5",

language = "English (US)",

volume = "29",

pages = "235--238",

journal = "Journal of Biomechanics",

issn = "0021-9290",

publisher = "Elsevier Ltd",

number = "2",

}

TY - JOUR

T1 - Stepwise regression is an alternative to splines for fitting noisy data

AU - Burkholder, Thomas J.

AU - Lieber, Richard L.

N1 - Funding Information: Acknowledgements-This work was supported by the Veterans Administration and NIH grants AR35192 and AR40050. We thank Drs Greg Loren and Scott Shoemaker for helpful discussions.

PY - 1996/2

Y1 - 1996/2

N2 - In this study, we compared numerical methods that are used to fit noisy data. Comparisons included polynominal regression, stepwise polynomial regression and quintic spline approximation. The advantages and limitations of each method are discussed in terms of curve fit quality, computational speed and ease, and solution compactness, Overall, the spline approximation and stepwise polynomial regression provide the best fits to the data. Stepwise regression provides the added utility of providing a simple, unconstrained function which can be easily implemented in simulation studies.

AB - In this study, we compared numerical methods that are used to fit noisy data. Comparisons included polynominal regression, stepwise polynomial regression and quintic spline approximation. The advantages and limitations of each method are discussed in terms of curve fit quality, computational speed and ease, and solution compactness, Overall, the spline approximation and stepwise polynomial regression provide the best fits to the data. Stepwise regression provides the added utility of providing a simple, unconstrained function which can be easily implemented in simulation studies.

UR - http://www.scopus.com/inward/record.url?scp=0030088019&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030088019&partnerID=8YFLogxK

U2 - 10.1016/0021-9290(95)00044-5

DO - 10.1016/0021-9290(95)00044-5

M3 - Article

C2 - 8849817

AN - SCOPUS:0030088019

SN - 0021-9290

VL - 29

SP - 235

EP - 238

JO - Journal of Biomechanics

JF - Journal of Biomechanics

IS - 2

ER -

Stepwise regression is an alternative to splines for fitting noisy data

Abstract

Funding

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this