Users' Guides to the Medical Literature
Guyatt G, Rennie D, Meade MO, Cook DJ
Part F Summarizing the Evidence
Chapter 20.3. Making Sense of Variability in Study Results
Victor Montori, Rose Hatala, John Ioannidis, Maureen O. Meade, Peter Wyer, Gordon Guyatt
Sections:
Arriving at a Single Summary Estimate of Effect, The Dilemma of Variability: Heterogeneity in Study Results, Visual Assessment of Variability, Yes-or-No Statistical Tests of Heterogeneity, Magnitude of Heterogeneity Statistical Tests, What to Do When Between-Study Variability in Results Is Large, Acknowledgment, References
Topics Discussed:
systematic reviews, tests of heterogeneity (variability in results)
Excerpt:
"Clinicians often approach the medical literature to find a single
key piece of information. This information may be the effect of
a treatment, the effect of a potentially harmful exposure,
the information provided by a diagnostic test, or the association
between a particular patient characteristic and the patient's prognosis. Each study provides a point estimate of that effect. However, point
estimates from related studies inevitably vary to some extent. The
primary goal of a quantitative systematic review,
also called a meta-analysis, is to provide
a single, best summary estimate of effect. To provide such an estimate,
reviewers will statistically combine results across studies in a meta-analysis...."
Log in to read the full chapter:
Get full access to JAMAevidence two ways:
Subscribe to JAMAevidence
JAMAevidence is a subscription-
based website dedicated to the learning, teaching, and practicing of evidence-based medicine.
Pay Per View
Timed access to all of JAMAevidence
24 hours for $29.95
48 hours for $49.95