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

Imputing response rates from means and standard deviations in meta-analyses.

Toshi A Furukawa1, Andrea Cipriani, Corrado Barbui

  • 1Department of Psychiatry, Nagoya City University Medical School, Mizuho-cho, Mizuho-ku, Nagoya, Japan. furukawa@med.nagoya-cu.ac.jp

International Clinical Psychopharmacology
|December 17, 2004
PubMed
Summary

This study demonstrates a method to impute missing response rates in meta-analyses using continuous outcome data. This approach ensures robust intention-to-treat analysis, improving treatment effect estimation.

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

Mapping 2-Year Psychiatric and Neurologic Risks After Infections Across Body Systems and Age Groups.

JAMA psychiatry·2026
Same author

A Decision-Support System for Personalized Antidepressant Treatment in Major Depressive Disorder-Reply.

JAMA·2026
Same author

Acceptability and accuracy of point-of-care monitoring of lithium levels.

The British journal of psychiatry : the journal of mental science·2026
Same author

Psychotherapy, Antidepressants, and Combined Treatment for Depression: A Network Meta-analysis on Social Functioning Outcomes.

Psychotherapy and psychosomatics·2026
Same author

Tool for Converting ADHD Rating Scales Scores Based on Individual Participant Data from 53 Randomized Controlled Trials of ADHD Medications.

Journal of child and adolescent psychopharmacology·2026
Same author

The GALENOS approach to triangulating evidence: a structured approach for integrating information from human and animal studies.

BMC medical research methodology·2026

Area of Science:

  • Biostatistics
  • Clinical Trials
  • Psychiatric Research

Background:

  • Intention-to-treat (ITT) analysis is crucial for randomized controlled trials and meta-analyses.
  • Imputing missing data for ITT in meta-analyses, especially for dichotomous outcomes, lacks established methods.
  • Sensitivity analyses like best-case/worst-case are potential strategies for handling missing data.

Purpose of the Study:

  • To empirically assess the appropriateness of converting continuous outcomes into dichotomous response rates for meta-analysis.
  • To evaluate the feasibility of imputing response rates from continuous data (mean+/-SD) for intention-to-treat analysis.
  • To determine if imputed response rates maintain the integrity of pooled relative risks in meta-analyses.

Main Methods:

  • Four meta-analyses of depression and anxiety studies with continuous outcomes (mean+/-SD) were analyzed.

Related Experiment Videos

  • Continuous outcomes were dichotomized into response rates, assuming normal distribution.
  • Intraclass correlation coefficient (ICC) was used to measure agreement between observed and imputed responders.
  • Pooled relative risks were calculated using both observed and imputed data.

    • Main Results:

    • A high agreement (ICC=0.97) was found between observed and imputed raw numbers of responders.
    • Pooled relative risks derived from imputed values were nearly identical to those from observed values.
    • The imputation method proved effective for handling missing response rates.

    Conclusions:

    • Converting continuous outcomes (mean+/-SD) to dichotomous response rates is a viable method for imputing missing data in meta-analyses.
    • This imputation strategy allows for robust intention-to-treat analysis, even when response rates are not directly reported.
    • The approach facilitates more reliable and clinically meaningful estimations of treatment effects in meta-analyses.