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

Multilevel factorial designs with experiment-induced clustering.

Inbal Nahum-Shani1, John J Dziak2, Linda M Collins3

  • 1Institute for Social Research, University of Michigan.

Psychological Methods
|April 7, 2017
PubMed
Summary

Factorial experiments in behavioral science can be powerful even with experiment-induced clustering (EIC). This study provides new power planning resources for these complex designs, bridging a critical gap in research methodology.

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

How and when do work stressors and peer norms impact career entrants' alcohol-related behavior and its consequences?

Human relations; studies towards the integration of the social sciences·2026
Same author

Mobile intervention for emerging adults with regular cannabis use: a micro-randomized trial.

Lancet regional health. Americas·2026
Same author

Antecedents and consequences of different indicators of engagement with a digital intervention for tobacco cessation.

NPJ digital medicine·2026
Same author

Effective monitoring of online AI decision-making algorithms in just-in-time adaptive interventions.

NPJ digital medicine·2026
Same author

Platform trial of smartphone-based cognitive-behavioural therapy (CBT) for depressive symptoms among people with no or subthreshold depression: a protocol for the Best, Efficient and Affordable Training in Resilience in Constant Evolution (BEATRICE) platform trial.

BMJ open·2026
Same author

Clinical Pharmacists, Medications, and Contingency Management for Targeting Smoking in HIV Clinics: A Randomized Clinical Trial.

JAMA network open·2026

Area of Science:

  • Behavioral Sciences
  • Psychology
  • Intervention Development

Background:

  • Factorial experimental designs are crucial for developing and optimizing multicomponent behavioral interventions.
  • A challenge arises when individuals are clustered within groups, leading to dependent data.
  • Existing power planning resources do not adequately address experiment-induced clustering (EIC).

Purpose of the Study:

  • To bridge the gap between experiment-induced clustering (EIC) and factorial experimental designs.
  • To extend existing EIC models to factorial experiments.
  • To provide power formulas for planning factorial experiments with EIC.

Main Methods:

  • Extending prior models for experiment-induced clustering (EIC) from single-factor to factorial experiments.

Related Experiment Videos

  • Developing power formulas for factorial designs involving EIC.
  • Demonstrating the feasibility and power of such designs.

    • Main Results:

    • Factorial experiments can be powerful and feasible despite experiment-induced clustering (EIC).
    • New power planning resources are introduced for factorial experiments with EIC.
    • The study extends EIC models to accommodate factorial designs.

    Conclusions:

    • Factorial experiments with EIC are feasible and can yield powerful results.
    • The developed methods and power formulas aid researchers in planning complex behavioral intervention studies.
    • This work addresses a significant limitation in the statistical power analysis for factorial designs with EIC.