TY - JOUR
AU1 - Berlin, Jesse A.
AU2 - Golub, Robert M.
AB - Opinion Editorials represent the opinions of the authors and JAMA EDITORIAL and not those of the American Medical Association. Building a Better Pyramid Jesse A. Berlin, ScD; Robert M. Golub, MD In following the practice of evidence-based medicine, when ponents (eg, diversity in patient populations or interventions) faced with a question about prevention or treatment the cli- and statistical components (eg, random differences). There are nician should seek out the best evidence that addresses the statistical approaches to try to quantify some elements of question. If quality of evi- heterogeneity, including the Q statistic (a measure of total dence is considered a pyra- within-study variance), the I statistic (the ratio of variability mid, what category should of results among studies to total observed variation), and τ Related article page 623 be placed at the peak? One (a measure of between-studies variance). Heterogeneity can dogma argues that it is the best-conducted randomized clini- be investigated and sometimes managed, but not eliminated cal trial (RCT) comprising patients similar to those seen by as an issue. In some instances, helpful insights can be gained the clinician, reasoning that a well-done RCT mimics pure when the heterogeneity of findings of component studies can 
TI - Meta-analysis as Evidence
JF - JAMA
DO - 10.1001/jama.2014.8167
DA - 2014-08-13
UR - https://www.deepdyve.com/lp/american-medical-association/meta-analysis-as-evidence-UKD30OpKIy
SP - 603
EP - 606
VL - 312
IS - 6
DP - DeepDyve
ER -