Login / Signup

Comparison of statistical methods used to meta-analyse results from interrupted time series studies: an empirical study.

Elizabeth KorevaarSimon Lee TurnerAndrew B ForbesAmalia KarahaliosMonica TaljaardJoanne E McKenzie
Published in: BMC medical research methodology (2024)
Our empirical study showed that meta-analysis effect estimates, their standard errors, confidence interval widths and p-values can be affected by statistical method choice. These differences may importantly impact interpretations and conclusions of a meta-analysis and suggest that the statistical methods are not interchangeable in practice.
Keyphrases
  • systematic review
  • healthcare
  • patient safety
  • case control
  • quality improvement
  • drug induced