Premium
Detecting outlying trials in network meta‐analysis
Author(s) -
Zhang Jing,
Fu Haoda,
Carlin Bradley P.
Publication year - 2015
Publication title -
statistics in medicine
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.996
H-Index - 183
eISSN - 1097-0258
pISSN - 0277-6715
DOI - 10.1002/sim.6509
Subject(s) - pairwise comparison , computer science , outlier , meta analysis , contrast (vision) , bayesian probability , data set , bayesian network , data mining , set (abstract data type) , scope (computer science) , statistics , econometrics , artificial intelligence , machine learning , mathematics , medicine , programming language
Network meta‐analysis (NMA) expands the scope of a conventional pairwise meta‐analysis to simultaneously handle multiple treatment comparisons. However, some trials may appear to deviate markedly from the others and thus be inappropriate to be synthesized in the NMA. In addition, the inclusion of these trials in evidence synthesis may lead to bias in estimation. We call such trials trial‐level outliers . To the best of our knowledge, while heterogeneity and inconsistency in NMA have been extensively discussed and well addressed, few previous papers have considered the proper detection and handling of trial‐level outliers. In this paper, we propose several Bayesian outlier detection measures, which are then applied to a diabetes data set. Simulation studies comparing our approaches in both arm‐based and contrast‐based model settings are provided in two supporting appendices. Copyright © 2015 John Wiley & Sons, Ltd.