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 and sample size calculations for studies involving linear regression

W D Dupont1, W D Plummer

  • 1Department of Preventive Medicine, Vanderbilt University School of Medicine, Nashville, Tennessee 37232-2637, USA.

Controlled Clinical Trials
|January 6, 1999
PubMed
Summary

This study provides methods for sample size and power calculations in linear regression studies, crucial for designing clinical trials and observational research. It offers a practical computer program to aid researchers in determining necessary sample sizes and statistical power.

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

Increased blood pressure visit-to-visit variability in patients with systemic lupus erythematosus: association with inflammation and comorbidity burden.

Lupus·2019
Same author

Analysis of factor VIII gene inversion mutations in 166 unrelated haemophilia A families: frequency and utility in genetic counselling.

Haemophilia : the official journal of the World Federation of Hemophilia·2016
Same author

The diagnosis of adult-onset haemophagocytic lymphohistiocytosis: lessons learned from a review of 29 cases of bone marrow haemophagocytosis in two large academic institutions.

Journal of clinical pathology·2016
Same author

Aging mice have increased chromosome instability that is exacerbated by elevated Mdm2 expression.

Oncogene·2011
Same author

Immunohistochemical analysis of receptor tyrosine kinase signal transduction activity in chordoma.

Neuropathology and applied neurobiology·2007
Same author

Estimating the undetected burden of influenza hospitalizations in children.

Epidemiology and infection·2006

Area of Science:

  • Biostatistics
  • Clinical Trial Design
  • Regression Analysis

Background:

  • Accurate sample size and power calculations are essential for the validity and efficiency of research studies, particularly in clinical trials.
  • Existing methods for sample size determination in linear regression may not cover all study designs or adequately address specific research questions.
  • The need for accessible tools to perform these calculations is critical for researchers across various scientific disciplines.

Purpose of the Study:

  • To present robust methods for sample size and power calculations specifically tailored for studies employing linear regression.
  • To provide guidance for studies aiming to detect specific regression slopes or differences between regression lines.
  • To offer a user-friendly computer program to facilitate these statistical calculations for researchers.

Related Experiment Videos

Main Methods:

  • Development of calculation methods for sample size and power in simple and multiple linear regression.
  • Consideration of scenarios where independent variables are specified or observationally determined, including estimation of their standard deviations.
  • Comparison with established methods, such as Cohen's approach for multiple linear regression.

Main Results:

  • The study outlines practical approaches for sample size and power calculations applicable to both experimental and observational linear regression studies.
  • A publicly available computer program is introduced, capable of determining sample size, power, or detectable alternative hypotheses.
  • The program offers context-specific help, making complex calculations more accessible.

Conclusions:

  • The presented methods and accompanying software provide valuable tools for researchers conducting studies involving linear regression.
  • These resources enhance the ability to design studies with adequate statistical power, increasing the likelihood of detecting meaningful effects.
  • The accessibility of the computer program democratizes sophisticated statistical planning for a wider research community.