TY - JOUR
T1 - AHRQ series on complex intervention systematic reviews—paper 5
T2 - advanced analytic methods
AU - Pigott, Terri
AU - Noyes, Jane
AU - Umscheid, Craig A.
AU - Myers, Evan
AU - Morton, Sally C.
AU - Fu, Rongwei
AU - Sanders-Schmidler, Gillian D.
AU - Devine, Beth
AU - Murad, M. Hassan
AU - Kelly, Michael P.
AU - Fonnesbeck, Christopher
AU - Kahwati, Leila
AU - Beretvas, S. Natasha
N1 - Publisher Copyright:
© 2017 The Author(s)
PY - 2017/10
Y1 - 2017/10
N2 - Background and Objective Advanced analytic methods for synthesizing evidence about complex interventions continue to be developed. In this paper, we emphasize that the specific research question posed in the review should be used as a guide for choosing the appropriate analytic method. Methods We present advanced analytic approaches that address four common questions that guide reviews of complex interventions: (1) How effective is the intervention? (2) For whom does the intervention work and in what contexts? (3) What happens when the intervention is implemented? and (4) What decisions are possible given the results of the synthesis? Conclusion The analytic approaches presented in this paper are particularly useful when each primary study differs in components, mechanisms of action, context, implementation, timing, and many other domains.
AB - Background and Objective Advanced analytic methods for synthesizing evidence about complex interventions continue to be developed. In this paper, we emphasize that the specific research question posed in the review should be used as a guide for choosing the appropriate analytic method. Methods We present advanced analytic approaches that address four common questions that guide reviews of complex interventions: (1) How effective is the intervention? (2) For whom does the intervention work and in what contexts? (3) What happens when the intervention is implemented? and (4) What decisions are possible given the results of the synthesis? Conclusion The analytic approaches presented in this paper are particularly useful when each primary study differs in components, mechanisms of action, context, implementation, timing, and many other domains.
KW - Bayesian analysis
KW - Decision analysis
KW - Finite mixture models
KW - Meta-analysis
KW - Meta-regression
KW - Qualitative synthesis
KW - Systematic review
UR - http://www.scopus.com/inward/record.url?scp=85028070287&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85028070287&partnerID=8YFLogxK
U2 - 10.1016/j.jclinepi.2017.06.015
DO - 10.1016/j.jclinepi.2017.06.015
M3 - Article
C2 - 28720512
AN - SCOPUS:85028070287
SN - 0895-4356
VL - 90
SP - 37
EP - 42
JO - Journal of Clinical Epidemiology
JF - Journal of Clinical Epidemiology
ER -