Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

The problem of the type II statistical error

R Mittendorf¹, V Arun, A M Sapugay

¹Department of Obstetrics and Gynecology, Chicago Lying-in Hospital, Illinois, USA.

Obstetrics and Gynecology

|November 1, 1995

Summary

Type II statistical errors, or beta errors, are common in clinical research due to insufficient sample sizes. A priori power calculations were rarely documented in published studies, suggesting a need for this practice.

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

Eco-friendly fabrication of ZnO-Co₃O₄/C S-scheme photocatalyst from bimetallic ZIF for sunlight-powered H₂ generation and CO₂-to-fuel conversion.

Scientific reports·2026

Same author

The role of social media, influencers, and online communities in blood donor recruitment and retention: A systematic scoping review.

Transfusion clinique et biologique : journal de la Societe francaise de transfusion sanguine·2026

Same author

Easy Access to Bioorthogonal Click-to-Release Reagent Bishydroxy-<i>trans</i>-cyclooctene (C<sub>2</sub>TCO) and Harnessing of Its Rapid Labeling and Dissecting Feature in Multicycle Imaging.

Bioconjugate chemistry·2025

Same author

Modified Arteriovenous Loop Technique for Successful Antegrade Device Closure of Perimembranous Ventricular Septal Defects with Aortic Valve Prolapse-A Single-Center Experience.

Pediatric cardiology·2025

Same author

Dissolved load, chemical weathering, and CO<sub>2</sub> uptake dynamics of small tropical mountainous rivers of Southern Granulite Terrain, Karamana and Vamanpuram, Western Ghats, India.

Scientific reports·2025

Same author

Exploring okra-derived compounds as prospective aromatase inhibitors: a computational study for enhanced breast cancer therapy.

Journal of biomolecular structure & dynamics·2024

Area of Science:

Clinical Research Methodology
Statistical Analysis in Medicine
Evidence-Based Practice

Background:

Type II statistical errors (beta errors) occur when a study fails to detect a true treatment effect due to inadequate sample size.
This issue is critical in clinical research, potentially delaying the adoption of effective treatments.
Previous research has not extensively quantified the prevalence of type II errors in published clinical studies.

Purpose of the Study:

To investigate the frequency of type II statistical errors in published clinical research.
To assess the documentation of a priori power calculations as an indicator of potential type II errors.

Main Methods:

A systematic search of Medline identified ten meta-analyses published between 1986 and 1994.

Related Experiment Videos

Component studies within these meta-analyses were examined for documented a priori power calculations.

Studies with negative findings, differing from meta-analysis conclusions, were scrutinized for potential type II errors.

Main Results:

Only 6.5% of component studies (15 of 231) documented a priori power calculations.
This low rate suggests many studies reporting no treatment effect may have been underpowered due to small sample sizes.
Documentation of power calculations was slightly higher in the 1980s-1990s (7.9%) compared to the 1960s-1970s (1.9%).

Conclusions:

The study highlights a significant problem with type II statistical errors in published clinical research.
A priori power calculations are essential for ensuring the reliability of study findings and the efficient introduction of effective treatments.
Implementing mandatory a priori power calculations in quantitative clinical research is recommended.