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

Seven ways to increase power without increasing N

W B Hansen1, L M Collins

  • 1Department of Public Health Sciences, Bowman Gray School of Medicine, Winston-Salem, NC 27157-1063, USA.

NIDA Research Monograph
|January 1, 1994
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

Review: Smart agri-systems for the pig industry.

Animal : an international journal of animal bioscience·2022
Same author

Recruiting and retaining first-year college students in online health research: Implementation considerations.

Journal of American college health : J of ACH·2022
Same author

Modelling the links between farm characteristics, respiratory health and pig production traits.

Scientific reports·2021
Same author

Influence of temperature on prevalence of health and welfare conditions in pigs: time-series analysis of pig abattoir inspection data in England and Wales.

Epidemiology and infection·2020
Same author

Optimizing the stimulus presentation paradigm design for the P300-based brain-computer interface using performance prediction.

Journal of neural engineering·2017
Same author

Applying dynamic data collection to improve dry electrode system performance for a P300-based brain-computer interface.

Journal of neural engineering·2016
Same journal

EVALUATION OF DRUG ABUSE TREATMENT MEDICATIONS: CONCORDANCE BETWEEN CLINICAL AND PRECLINICAL STUDIES.

NIDA research monograph·2006
Same journal

Problems of drug dependence 1999: Proceedings of the 61st annual scientific meeting, the College on Problems of Drug Dependence, Inc.

NIDA research monograph·2001
Same journal

Problems of drug dependence 1997: proceedings of the 59th annual scientific meeting.

NIDA research monograph·1998
Same journal

Laboratory Behavioral Studies of Vulnerability to Drug Abuse. Proceedings of a meeting. August 2-3, 1994.

NIDA research monograph·1998
Same journal

Disaggregating the liability for drug abuse.

NIDA research monograph·1998
Same journal

Integrating genetic and behavioral models in the study of substance abuse mechanisms.

NIDA research monograph·1998
See all related articles

Prevention researchers often overlook statistical power, leading to underpowered studies. Focusing solely on sample size (N) is insufficient; strategies to maintain effective sample size and maximize effect size are crucial for adequate statistical power.

Area of Science:

  • Prevention Science
  • Biostatistics
  • Research Methodology

Background:

  • Statistical power is a critical research consideration, especially for National Institute on Drug Abuse (NIDA) grantees.
  • Despite awareness, prevention researchers frequently fail to achieve adequate statistical power in completed studies.
  • Previous reviews indicate a widespread lack of statistical power across various research topics.

Purpose of the Study:

  • To address the observed deficit in statistical power within prevention research.
  • To argue against the overemphasis on sample size (N) as the sole method for increasing statistical power.
  • To propose alternative strategies for enhancing statistical power beyond sample size adjustments.

Main Methods:

  • Analysis of statistical power in 46 longitudinal prevention cohorts using nonparametric assumptions.

Related Experiment Videos

  • Examination of power requirements for detecting treatment and control group differences.
  • Review of power for detecting pre-post change in substance use within cohorts.

    • Main Results:

    • Many studies lack sufficient power; detecting an 8-16% difference requires 80% power.
    • Detecting pre-post change necessitated over 100% reduction in 22 of 46 cohorts for 80% power.
    • Thirty-three cohorts had less than 50% power to detect a 50% reduction in substance use.

    Conclusions:

    • Prevention research often suffers from inadequate statistical power despite awareness of its importance.
    • Over-reliance on increasing sample size (N) is a primary reason for insufficient power.
    • Researchers should focus on maintaining effective sample size and maximizing effect size to improve statistical power.