Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Stepwise regression is an alternative to splines for fitting noisy data

T J Burkholder1, R L Lieber

  • 1Department of Orthopaedics, University of California and Veterans Administration Medical Center, San Diego, USA.

Journal of Biomechanics
|February 1, 1996
PubMed
Summary

This study compared numerical methods for fitting noisy data, finding quintic spline approximation and stepwise polynomial regression offer the best curve fits. Stepwise regression is particularly useful for simulations due to its simple function.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

What the PCSA? Addressing diversity in lower-limb musculoskeletal models: age- and sex-related differences in PCSA and muscle mass.

Journal of biomechanics·2025
Same author

[Surgical and biological techniques in cerebral palsy].

Rehabilitacion·2022
Same author

The mechanical strength of side-to-side tendon repair with mismatched tendon size and shape.

The Journal of hand surgery, European volume·2014
Same author

Simultaneous powering of forearm pronation and key pinch in tetraplegia using a single muscle-tendon unit.

The Journal of hand surgery, European volume·2011
Same author

A nonlinear model of passive muscle viscosity.

Journal of biomechanical engineering·2011
Same author

Novel applications of external anal sphincter muscle sarcomere length to enhance the anal canal function.

Neurogastroenterology and motility·2010

Area of Science:

  • Data analysis and numerical methods
  • Statistical modeling and regression analysis
  • Computational mathematics

Background:

  • Noisy data presents challenges in accurate scientific modeling.
  • Various numerical methods exist for data fitting, each with unique strengths and weaknesses.
  • Evaluating these methods is crucial for selecting appropriate analytical techniques.

Purpose of the Study:

  • To compare the performance of different numerical methods for fitting noisy datasets.
  • To assess polynomial regression, stepwise polynomial regression, and quintic spline approximation.
  • To evaluate methods based on curve fit quality, computational efficiency, and ease of implementation.

Main Methods:

  • Comparative analysis of numerical fitting techniques.

Related Experiment Videos

  • Implementation of polynomial regression.
  • Application of stepwise polynomial regression.
  • Utilization of quintic spline approximation.

    • Main Results:

    • Quintic spline approximation and stepwise polynomial regression yielded superior fits to noisy data.
    • Polynomial regression showed limitations in fitting complex or noisy datasets.
    • Stepwise regression offers a simple, unconstrained function suitable for simulation studies.

    Conclusions:

    • Quintic spline approximation and stepwise polynomial regression are recommended for fitting noisy data.
    • Stepwise polynomial regression provides a practical tool for simulation modeling.
    • The choice of method depends on specific application requirements regarding accuracy and computational resources.