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

Effect modification by time-varying covariates.

James M Robins1, Miguel A Hernán, Andrea Rotnitzky

  • 1Department of Epidemiology, Harvard School of Public Health, Boston, MA 02115, USA.

American Journal of Epidemiology
|September 19, 2007
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

Towards a Unified Theory for Semiparametric Data Fusion with Individual-Level Data.

Annals of statistics·2026
Same author

Methodological Approaches to Real-World Evidence Generation for Glucagon-like Peptide-1-Based Therapies: Synopsis of a National Institute of Diabetes and Digestive and Kidney Diseases Workshop.

Annals of internal medicine·2026
Same author

Global Sensitivity Analysis for Studies Extending Inferences From a Randomized Trial to a Target Population.

Statistics in medicine·2026
Same author

Statins and risk of cardiovascular disease: Emulating a primary prevention trial in breast cancer survivors.

Journal of the National Cancer Institute·2026
Same author

Long-term effects of colonoscopy screening on colorectal cancer incidence and mortality: a multicountry, population-based randomised controlled trial.

Lancet (London, England)·2026
Same author

Extending inferences from a randomized trial to trial-eligible and treatment-candidate target populations: examples of generalizability and transportability.

Epidemiology (Cambridge, Mass.)·2026
Same journal

A SIMPLE AND POWERFUL TEST OF VACCINE WANING.

American journal of epidemiology·2026
Same journal

Association Between maternal body mass index, offspring growth and pubertal timing: results from a longitudinal birth cohort study.

American journal of epidemiology·2026
Same journal

Correction to: Developing a novel algorithm to identify incident and prevalent dementia in Medicare claims-the ARIC Study.

American journal of epidemiology·2026
Same journal

RE: advancing observational research on arts and health: theory-informed approaches using the RADIANCE framework.

American journal of epidemiology·2026
Same journal

Maternal Cesarean Section and Offspring ASD or ADHD Risk: A Nurses' Health Study II Analysis.

American journal of epidemiology·2026
Same journal

Immigration and epigenetic age acceleration in the health and retirement study: differences Between Hispanics and Non-Hispanics.

American journal of epidemiology·2026
See all related articles

Structural nested models (SNMs) are better for analyzing time-varying covariate effects than marginal structural models (MSMs). History-adjusted MSMs may yield contradictory conclusions, necessitating a refined definition for accurate effect modification analysis.

Area of Science:

  • Epidemiology
  • Biostatistics
  • Causal Inference

Background:

  • Marginal structural models (MSMs) are suitable for baseline covariate effect modification but limited for time-varying covariates.
  • Structural nested models (SNMs) were developed to address effect modification by time-varying covariates.
  • History-adjusted MSMs (HA-MSMs) were proposed as a generalization of MSMs for time-varying covariates.

Purpose of the Study:

  • To compare the utility of history-adjusted marginal structural models (HA-MSMs) and structural nested models (SNMs) for examining effect modification by time-dependent covariates.
  • To propose a more restrictive definition of HA-MSMs to address potential logical incompatibilities.
  • To evaluate the advantages and disadvantages of HA-MSMs versus SNMs in the context of time-dependent effect modification.

Related Experiment Videos

Main Methods:

  • Comparison of statistical modeling approaches: HA-MSMs and SNMs.
  • Analysis of potential logical incompatibilities and contradictory conclusions arising from HA-MSMs.
  • Refinement of the definition of HA-MSMs for improved applicability.

Main Results:

  • Standard HA-MSMs can lead to logically incompatible parameter estimates and contradictory substantive conclusions.
  • SNMs are specifically designed for and better suited to estimating effect modification by time-varying covariates.
  • A more restrictive definition of HA-MSMs may mitigate some issues but SNMs remain a preferred approach for this specific problem.

Conclusions:

  • SNMs are the recommended approach for estimating effect modification by time-varying covariates due to their inherent design.
  • Researchers should be cautious when using HA-MSMs for time-varying effect modification, as they can produce inconsistent results.
  • Further refinement and careful application are needed if HA-MSMs are to be used for time-dependent effect modification analysis.