作者: Binod Neupane , Danielle Richer , Ashley Joel Bonner , Taddele Kibret , Joseph Beyene
DOI: 10.1371/JOURNAL.PONE.0115065
关键词: Software engineering 、 Usability 、 Software 、 Computer science 、 Set (abstract data type) 、 Meta-analysis 、 Package development process 、 Meta-Analysis as Topic 、 Inference 、 Process (engineering) 、 Bioinformatics
摘要: Network meta-analysis (NMA) – a statistical technique that allows comparison of multiple treatments in the same simultaneously has become increasingly popular medical literature recent years. The methodology underpinning this and software tools for implementing methods are evolving. Both commercial freely available packages have been developed to facilitate computations using NMA with varying degrees functionality ease use. This paper aims introduce reader three R packages, namely, gemtc, pcnetmeta, netmeta, which implemented R. Each automates process performing so users can perform analysis minimal computational effort. We present, compare contrast availability different important features these clinical investigators researchers determine implement depending on their needs. Four summary tables detailing (i) data input network plotting, (ii) modeling options, (iii) assumption checking diagnostic testing, (iv) inference reporting tools, provided, along an previously published dataset illustrate outputs from each package. demonstrate provides useful set combined provide nearly all might be desired when conducting NMA.