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

Local estimation of smooth curves for longitudinal data

R A Betensky1

  • 1Department of Biostatistics, Harvard School of Public Health, Boston, Massachusetts 02115, USA.

Statistics in Medicine
|November 19, 1997
PubMed
Summary

This study introduces a flexible local likelihood method for analyzing longitudinal growth data. It effectively estimates smooth population and individual growth curves, even with incomplete or irregularly timed measurements, offering a robust alternative to traditional polynomial models.

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

Accounting for incomplete testing in the estimation of epidemic parameters.

medRxiv : the preprint server for health sciences·2020
Same author

Nonidentifiability in the presence of factorization for truncated data.

Biometrika·2019
Same author

Hypothesis Tests for Neyman's Bias in Case-Control Studies.

Journal of applied statistics·2018
Same author

Gain of chromosome arm 1q in atypical meningioma correlates with shorter progression-free survival.

Neuropathology and applied neurobiology·2011
Same author

Urinary biomarkers in the early diagnosis of acute kidney injury.

Kidney international·2007
Same author

Predicting short-term disability in multiple sclerosis.

Neurology·2007

Area of Science:

  • Biostatistics
  • Longitudinal Data Analysis
  • Growth Curve Modeling

Background:

  • Traditional mixed-effects models often assume polynomial growth curves, which may not accurately fit complex biological or technical data.
  • Lack of known mechanistic models or limitations of polynomial fits necessitate more flexible curve estimation approaches for longitudinal data.

Purpose of the Study:

  • To develop and apply a flexible method for estimating smooth population and individual growth curves from longitudinal data.
  • To address limitations of traditional models by accommodating non-polynomial and non-linear growth patterns.
  • To provide a robust approach for analyzing incomplete or irregularly spaced longitudinal measurements.

Main Methods:

  • Application of the local likelihood estimation method by Tibshirani and Hastie.

Related Experiment Videos

  • Estimation of smooth population and individual growth curves by assuming local linearity or quadraticity within overlapping time windows.
  • Utilizing estimating equations for statistical inference on the estimated curves.

    • Main Results:

    • The local likelihood approach successfully estimates smooth growth curves without requiring complete data or uniform measurement time points.
    • Demonstrated applicability across diverse datasets, including biological (serum neopterin), medical device (dialyser ultrafiltration), and physiological (lung volume) measurements.
    • The method is computationally accessible using standard statistical software.

    Conclusions:

    • The local likelihood method offers a flexible and robust alternative for longitudinal growth curve analysis, outperforming rigid polynomial assumptions.
    • This approach enhances the ability to model complex growth trajectories and handle real-world data imperfections.
    • Facilitates descriptive analysis and statistical inference for longitudinal studies across various scientific domains.