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

Power considerations when a continuous outcome variable is dichotomized

B A Deyi1, A S Kosinski, S M Snapinn

  • 1Biostatistics and Research Data Systems, BL3-2, Merck Research Laboratories, West Point, Pennsylvania 19486, USA.

Journal of Biopharmaceutical Statistics
|May 23, 1998
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

In vivo intervertebral disc mechanical deformation following a treadmill walking "stress test" is inversely related to T1rho relaxation time.

Osteoarthritis and cartilage·2022
Same author

Improving vasomotor symptoms; psychological symptoms; and health-related quality of life in peri- or post-menopausal women through yoga: An umbrella systematic review and meta-analysis.

Complementary therapies in medicine·2017
Same author

Use of mindfulness, meditation and relaxation to treat vasomotor symptoms.

Climacteric : the journal of the International Menopause Society·2017
Same author

Effect of the CT table strap on radiation exposure and image quality during cervical spine CT.

AJNR. American journal of neuroradiology·2014
Same author

Following unenhanced MRI assessment for local recurrence after surgical resection of mesenchymal soft tissue tumors, do additional gadolinium-enhanced images change reader confidence or diagnosis?

European journal of radiology·2012
Same author

Applying the resource-based relative value scale to the Emory angioplasty versus surgery trial.

The American journal of cardiology·2002
Same journal

Correction.

Journal of biopharmaceutical statistics·2026
Same journal

Leveraging external controls in clinical trials: estimands, estimation, assumptions.

Journal of biopharmaceutical statistics·2026
Same journal

Special issue of nonclinical statistics in regulatory applications guest editors' notes.

Journal of biopharmaceutical statistics·2026
Same journal

Comparison of flexible parametric modeling and nonparametric methods to estimate restricted mean survival time: A simulation study.

Journal of biopharmaceutical statistics·2026
Same journal

Simulated treatment comparisons with jackknife pseudo values for estimating population-adjusted marginal treatment effects.

Journal of biopharmaceutical statistics·2026
Same journal

Sample sizes for randomized controlled trials utilizing Bayesian response adaptive randomization for continuous outcomes.

Journal of biopharmaceutical statistics·2026
See all related articles

Dichotomizing continuous variables in research significantly reduces statistical power. This power loss, particularly in comparing groups, can be substantial and depends on group means and chosen cutoffs.

Area of Science:

  • Biostatistics
  • Clinical Trial Design
  • Statistical Power Analysis

Background:

  • Continuous variables can be analyzed by comparing means or by dichotomizing them into categories.
  • Dichotomization of continuous data is common in clinical research, but its statistical implications are not always fully appreciated.

Purpose of the Study:

  • To investigate and quantify the loss of statistical power when continuous variables are dichotomized.
  • To analyze how power loss is influenced by the relationship between group means and the dichotomization cutoff point.

Main Methods:

  • The study focuses on normally distributed variables with known, common variances in two groups.
  • Mathematical analysis is used to determine the relationship between group means, cutoff points, and statistical power.

Related Experiment Videos

Main Results:

  • Power loss from dichotomization is not uniform; it varies from negligible to substantial.
  • The degree of power loss is critically dependent on the separation of the group means and the position of the cutoff point relative to these means.

Conclusions:

  • Dichotomizing continuous outcomes in clinical trials can lead to considerable loss of statistical power.
  • Changing the Lovastatin Restenosis Trial endpoint from dichotomous to continuous was justified due to significant power losses observed when comparing proportions.