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

Multiple linear regression with some correlated errors: classical and robust methods.

Ana M Pires1, Isabel M Rodrigues

  • 1Departamento de Matemática e CEMAT, Instituto Superior Técnico, Technical University of Lisbon (TULisbon), Av. Rovisco Pais, 049-001 Lisboa, Portugal. apires@math.ist.utl.pt

Statistics in Medicine
|December 13, 2006
PubMed
Summary
This summary is machine-generated.

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

Luminescent Ir<sup>III</sup>-Au<sup>I</sup> Heterobimetallic Complex with a Carbene Bridging Ligand.

Inorganic chemistry·2026
Same author

Nontoxic Dual-Function Probe for Ratiometric Oxygen Sensing and Cellular Imaging Based on Ir<sup>III</sup>-Eu<sup>III</sup>-Functionalized SiO<sub>2</sub> Particles.

ACS omega·2026
Same author

Engineering the Thermometric Response of Dinuclear Eu<sup>III</sup> Complexes via Terminal Ligand-Induced Nonradiative Processes.

ACS omega·2026
Same author

Editorial: Ensuring public health: the active role of healthcare professionals.

Frontiers in public health·2026
Same author

Castor oil and europium-based luminescent films for thermal sensing.

Frontiers in chemistry·2026
Same author

Synthesis and Characterization of Luminescent and Antibacterial Europium-Titanate nanotubes.

ACS omega·2026
Same journal

Interpretable Bayesian Modeling for Multireader Multicase Studies: Addressing Overdispersion and Limited Sample Size in Diagnostic Enhancement Evaluation.

Statistics in medicine·2026
Same journal

Adaptive Sequential Multiple Hypotheses Testing for Concomitant Vaccine Safety Surveillance.

Statistics in medicine·2026
Same journal

Novel Distance Regression for Repeated Outcomes With Missing Data: Applications to Longitudinal and Crossover Studies of Microbiome Beta-Diversity.

Statistics in medicine·2026
Same journal

Optimal Weighted Tests for Replication Studies and the 'Two-Trials Rule' With Multiple Hypotheses.

Statistics in medicine·2026
Same journal

Identifiable Copula-Double-Cox Models: A Fully Parametric Framework for Dependent Right-Censored Survival Data.

Statistics in medicine·2026
Same journal

Moving From Individualized Risk-Based Prevention to Benefit-Based Prevention: Estimating Individualized Life-Years Gained From Prevention Services as a Basis for Eligibility.

Statistics in medicine·2026
See all related articles

This study addresses correlated errors in multiple linear regression for scoliosis surgery data. Robust estimation methods proved most effective, handling outliers and heavy-tailed errors in medical datasets.

Area of Science:

  • Statistics
  • Medical Data Analysis
  • Biostatistics

Background:

  • Multiple linear regression is common but assumes independent errors.
  • Medical data, like scoliosis patient outcomes, can violate this assumption due to repeated measures.
  • Ignoring correlated errors can lead to inaccurate statistical inferences.

Purpose of the Study:

  • To develop and evaluate methods for estimating parameters in multiple linear regression with correlated errors.
  • To address challenges posed by medical datasets with potential outliers and non-normal error distributions.
  • To compare classical and robust estimation techniques in this context.

Main Methods:

  • Considered classical and robust estimation procedures for linear models with correlated errors.

Related Experiment Videos

  • Proposed maximum likelihood estimation assuming normal errors.
  • Developed a robustified estimation procedure using robust linear regression outputs.
  • Utilized diagnostics like the Durbin-Watson test to confirm error correlation.

    • Main Results:

    • The assumption of non-correlated errors was violated in the scoliosis dataset.
    • Both maximum likelihood and robustified methods were applied.
    • The robustified procedure demonstrated superior performance, effectively handling outlying observations and heavy-tailed error distributions.
    • This robust approach yielded the most satisfactory results for the analyzed medical data.

    Conclusions:

    • Correlated errors are a significant consideration in analyzing medical data with repeated observations.
    • Robust estimation methods offer a valuable alternative to classical approaches when data deviates from ideal assumptions.
    • The proposed robustified method is effective for parameter estimation in multiple linear regression with correlated errors, particularly in the presence of data anomalies.