A simulation study to compare different estimation approaches for network meta-analysis and corresponding methods to evaluate the consistency assumption

摘要

The combination of the results of several studies comparing the same two interventions is known as meta-analysis. The concept of meta-analysis and the corresponding methods are well established in medical statistics. However, in the recent years new methods for indirect comparisons have become more and more popular [ , ]. These comprise both the adjusted indirect comparison of two interventions, which have not been compared directly in a head-to-head-trial, and the simultaneous comparison of more than two interventions in a network of interventions.