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 Video

Updated: Jun 29, 2026

An R-Based Landscape Validation of a Competing Risk Model
05:37

An R-Based Landscape Validation of a Competing Risk Model

Published on: September 16, 2022

Validation of biomarker-based risk prediction models.

Jeremy M G Taylor1, Donna P Ankerst, Rebecca R Andridge

  • 1Department of Biostatistics, University of Michigan, 1420 Washington Heights, Ann Arbor, MI 48109, USA. jmgt@umich.edu

Clinical Cancer Research : an Official Journal of the American Association for Cancer Research
|October 3, 2008
PubMed
Summary

Assessing the validity of predictive models, especially those using biomarkers, is crucial. Rigorous external validation ensures models generalize to new populations, preventing overfitting and assay variation issues.

Related Concept Videos

Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches01:23

Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches

Biopharmaceutical studies constitute a vital field aiming to enhance drug delivery methods and refine therapeutic approaches, drawing upon diverse interdisciplinary knowledge. In research methodologies, the choice between controlled and non-controlled studies significantly influences the study's reliability and accuracy.
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast, controlled...

You might also read

Related Articles

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

Sort by
Same author

Gradient boosting-based discrete failure time model for selecting time-varying effects and interactions.

Lifetime data analysis·2026
Same author

Social Support, Loneliness, and Inflammation in LGB+ Subgroups: Health Disparities in a Partnered US Cohort.

Biopsychosocial science and medicine·2026
Same author

Self-rated health and inflammation: Associations among partnered sexual minority and heterosexual adults.

Health psychology : official journal of the Division of Health Psychology, American Psychological Association·2026
Same author

Corrigendum to "LGBTQ+ identity and its association with inflammation and cellular immune function". [Brain Behav. Immun. 126 (2025) 333-341].

Brain, behavior, and immunity·2026
Same author

Chemotherapy-induced estradiol reduction is associated with less relief of pre-chemotherapy anxiety in breast cancer patients.

Psychoneuroendocrinology·2026
Same author

α/β for Hepatocellular Carcinoma Tumors Treated With Radiation Therapy.

International journal of radiation oncology, biology, physics·2026

Area of Science:

  • Biostatistics
  • Medical Informatics
  • Epidemiology

Background:

  • Predictive models are increasingly used for decision-making.
  • Models with biomarkers face challenges like overfitting and interlaboratory assay variation.
  • Robust validation is essential for reliable model application.

Purpose of the Study:

  • To differentiate between internal and external statistical validation methods.
  • To emphasize the critical role of truly external validation for generalizability.
  • To review predictive model types, building strategies, and performance assessment measures.

Main Methods:

  • Distinguishing internal validation (e.g., cross-validation) from external validation.
  • Defining external validation as performance assessment on independent datasets from different institutions.

Related Experiment Videos

Last Updated: Jun 29, 2026

An R-Based Landscape Validation of a Competing Risk Model
05:37

An R-Based Landscape Validation of a Competing Risk Model

Published on: September 16, 2022

  • Highlighting the necessity of datasets completely separate from model development.

    • Main Results:

    • Internal validation is necessary but insufficient for assessing generalizability.
    • External validation provides a more rigorous evaluation of a model's performance in new settings.
    • Truly external datasets, uninfluenced by model development, are key for robust validation.

    Conclusions:

    • External validation is paramount for confirming predictive model generalizability.
    • Careful consideration of model types, building strategies, and multiple performance measures is recommended.
    • Ensuring data independence in external validation is critical for reliable results.