PulseExploreJournal ClubResearchersJournals
Instagram
HomeJournal ClubExplore
Synapse
⌘+K
Synapse
April 15, 1997Statistics in Medicine

Incorporating Variability in Estimates of Heterogeneity in the Random Effects Model in Meta-Analysis

View Full Paper
Ask AI
Bookmark
Share

Authors

BBBrad J. BiggerstaffRTRichard L. Tweedie

Discussion

Loading...

Member takes

Overview

Randomized trial investigates a new method for estimating heterogeneity in meta-analysis, suggesting improved weighting of studies' results.

Key Points

  • To propose a method that incorporates variability into estimates of heterogeneity in meta-analysis using random effects models.
  • Developed a form for the variance of Cochran's homogeneity statistic Q for interval estimation of tau 2.
  • Compared asymptotic likelihood methods with traditional methods for estimating heterogeneity.
  • Illustrated the new weighting scheme through two examples considering variations in study results.
  • The new weighting scheme balances between standard fixed and random effects models.
  • Large studies are down-weighted while small studies are up-weighted, adjusting for study differences.
  • Improved estimation of overall mean by accounting for variability in tau 2.

Cite This Study

Biggerstaff et al. (1997) studied this question.

synapsesocial.com/papers/6a10ad2c67e0c20fc6395ad4https://doi.org/10.1002/(sici)1097-0258(19970415)16:7<753::aid-sim494>3.0.co;2-g
View Full Paper
Ask AI
Bookmark
Share