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

Methods for categorizing a prognostic variable in a multivariable setting.

Madhu Mazumdar1, Alex Smith, Jennifer Bacik

  • 1Department of Epidemiology and Biostatistics, Memorial Sloan-Kettering Cancer Center, 1275 York Avenue, Box 44, New York, NY 10021, U.S.A. mazumdar@biost.mskcc.org

Statistics in Medicine
|February 19, 2003
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

Dosimetric Correlates of Acute Toxicities for Moderate Hypofractionated Whole-Breast Irradiation: Implications for ASTRO Planning Guidelines.

Advances in radiation oncology·2026
Same author

Virtual Nursing Pilot in the Inpatient Setting: Qualitative Evaluation.

JMIR nursing·2026
Same author

Enhancing conventional biopsies: ultrasound-guided percutaneous bone marrow biopsy and aspiration.

Journal of ultrasound·2026
Same author

CT Features of Gastric Dilatation-Volvulus in Guinea Pigs.

Veterinary radiology & ultrasound : the official journal of the American College of Veterinary Radiology and the International Veterinary Radiology Association·2026
Same author

Prospective Evaluation of Serial Biomarkers in Patients With Intermediate High Risk Acute Pulmonary Embolism: A Single Center Proof-of-Concept Study.

Pulmonary circulation·2026
Same author

COMPARATIVE EFFECTIVENESS OF PROPENSITY SCORE ESTIMATION METHODS FOR INVERSE PROBABILITY OF TREATMENT WEIGHTING ANALYSIS WITH COMPLEX SURVEY DATA: A SIMULATION STUDY.

Journal of survey statistics and methodology·2025
Same journal

A Mixture of Distributed Lag Non-Linear Models to Account for Spatially Heterogeneous Exposure-Lag-Response Associations.

Statistics in medicine·2026
Same journal

Practical Considerations for Gaussian Process Modeling for Causal Inference in Quasi-Experimental Studies With Panel Data.

Statistics in medicine·2026
Same journal

Covariate Adjustment for Wilcoxon Two Sample Statistic and Test.

Statistics in medicine·2026
Same journal

Beyond Fixed Thresholds: Optimizing Summaries of Wearable Device Data via Piecewise Linearization of Quantile Functions.

Statistics in medicine·2026
Same journal

A Causal Framework for Evaluating the Total Effect of Strategies Aiming to Expand Screening and to Improve Outcomes.

Statistics in medicine·2026
Same journal

Causal Effects on Nonterminal Event Time With Application to Antibiotic Usage and Future Resistance.

Statistics in medicine·2026
See all related articles

This study introduces multivariable cutpoint search methods for prognostic variables, improving accuracy in identifying optimal cutpoints and estimating effect sizes compared to traditional univariable approaches. The cross-validation method is recommended for its superior performance.

Area of Science:

  • Biostatistics
  • Medical Informatics
  • Epidemiology

Background:

  • Continuous prognostic variables are often categorized using univariable cutpoint searches before inclusion in multivariable models.
  • This approach may not accurately reflect the variable's prognostic value within the multivariable context.
  • The optimal cutpoint search might be biased when performed separately from the multivariable model fitting.

Purpose of the Study:

  • To extend univariable cutpoint search methods to the multivariable setting.
  • To evaluate the efficiency of multivariable cutpoint searches in identifying true cutpoints and estimating effect sizes.
  • To compare the performance of split-sample and cross-validation approaches in multivariable settings.

Main Methods:

  • Extension of split-sample and two-fold cross-validation approaches for cutpoint searching to a multivariable context.

Related Experiment Videos

  • Utilized the -2 x log-likelihood statistic as the measure for assessing the relationship between the prognostic variable and the outcome.
  • Conducted a Monte Carlo simulation study to compare method performance under various scenarios.

    • Main Results:

    • Both multivariable split-sample and cross-validation methods are more efficient than their univariable counterparts in detecting true cutpoints and estimating effect sizes.
    • The cross-validation method demonstrated superior performance over the split-sample method in both univariable and multivariable settings.
    • A notable loss of power was observed with the multivariable cross-validation method when a cutpoint model was used despite a continuous relationship between the covariate and outcome.

    Conclusions:

    • Performing cutpoint searches within the multivariable setting is more accurate and efficient for prognostic variables.
    • The multivariable cross-validation approach is recommended for its robust performance in identifying optimal cutpoints.
    • Awareness of potential power loss is crucial when applying cutpoint models in multivariable analyses, especially with continuous relationships.