The theoretical foundation of relevant packages of R software for network meta-analysis is mainly based on Bayesian statistical model and a few of them use generalized linear model. Network meta-analysis is performed using GeMTC R package through calling the corresponding rjags package, BRugs package, or R2WinBUGS package (namely, JAGS, OpenBUGS, and WinBUGS software, respectively). Meanwhile, GeMTC R package can generate data storage files for GeMTC software. Techonically, network meta-analysis is performed through calling the software based on Markov Chain Monte Carlo method. In this article, we briefly introduce how to use GeMTC R package to perform network meta-analysis through calling the OpenBUGS software.
Network plots can clearly present the relationships among the direct comparisons of various interventions in a network meta-analysis. Currently, there are some methods of drawing network plots. However, the information provided by a network plot and the interface-friendly degree to a user differ in the kinds of software. This article briefly introduces how to draw network plots using the network package and gemtc package that base on R Software, Stata software, and ADDIS software, and it also compares the similarities and differences among them.
R Software is an open, free of use and charge statistical software which has a powerful graphic capability; however, it requires more complex codes and commands to perform network meta-analysis, which causes errors and difficulties in operation. WinBUGS software is based on Bayesian theory, which has a powerful data processing capability, and especially its codes are simple and easy to operate for dealing with network meta-analysis. However, its function of illustrating statistical results is very poor. In order to fully integrate the advantages of R software and WinBUGS software, an R2WinBUGS package based on R software has been developed which builds a “bridge” across two of them, making network meta-analysis process conveniently, quickly and result illustration more beautiful. In this article, we introduced how to use the R2WinBUGS package for performing network meta-analysis using examples.
R software is a free and powerful statistical tool, including Metafor, Meta as well as Rmeta packages, all of which could conduct meta-analysis. Metafor package provides functions for meta-analyses which include analysis of continuous and categorical data, meta-regression, cumulative meta-analysis as well as test for funnel plot asymmetry. The package can also draw various plots, such as forest plot, funnel plot, radial plot and so forth. Mixed-effects models (involving single or multiple categorical and/or continuous moderates) can only be fitted with Metafor packages. Advanced methods for testing model coefficients and confidence intervals are also implemented only in this package. This article introduces detailed operation steps of Metafor package for meta-analysis using cases.
ObjectiveTo compare the characteristics and functions of the network meta-analysis software and for providing references for users. MethodsPubMed, CNKI, official website of Stata and R, and Google were searched to collect the software and packages that can perform network meta-analysis up to July 2014. After downloading the software, packages, and their user guides, we used the software and packages to calculate a typical example. The characteristics, functions, and computed results were compared and analyzed. ResultsFinally, 11 types of software were included, including programming and non-programming software. They were developed mainly based on Bayesian or Frequentist. Most types of software have the characteristics of easy to operate, easy to master, exactitude calculation, or good graphing; however, there is no software that has the exactitude calculation and good graphing at the same time, which needs two or more kinds of software combined to achieve. ConclusionWe suggest the user to choose the software at least according to personal programming basis and custom; and the user can consider to choose two or more kinds of software combined to finish the objective network meta-analysis. We also suggest to develop a kind of software which is characterized of fully function, easy operation, and free.
The goal of JAGS (Just Another Gibbs Sampler) software is to remedy the short of BUGS software that unable to running on a system besides Microsoft Windows, such as Unix or Linux. JAGS owns independent computing function and formula of Bayesian theory; it is mischaracterized with simple user interface, good system compatibility, smoother operation, and good interactivity with other programming software. However, due to the limitations of lacking function for results data reading and unscrambling and graph plotting, the popularization and application of JAGS software is restricted. Calling JAGS software from R software through R2jags package, rjags package, or runjags package can overcome these limitations. The operating principle of these three packages is calling JAGS software in the framework of the R software, they have similar functional structure and all have easy maneuverability, concise command, perfect function of data reading and unscrambling and graph drawing; however, there are some differences among them in practice. This article introduces how to performing network meta-analysis by calling JAGS software from R through these three packages.
The mada package is a type of package that is especially used for implementing meta-analysis of diagnostic accuracy tests. This package is developed on basis of classical statistical theories and it can be used to calculate all relevant effect size of diagnostic accuracy tests; however, it does not provide pooled values of sensitivity and specificity. This article uses an example to introduce the whole functions of mada package in implementing meta-analysis of diagnostic accuracy tests, including data preparation, calculation implementation, result summary, and plots drawing.
ObjectiveTo introduce sensitivity and homogeneity tests in network meta-analysis and its implementation in R software. MethodsUsing an example, we performed sensitivity analysis by comparing the random effect model with the fixed effect model. Homogeneity analysis was performed using metaphor package and combinat package in R software. ResultsThe results of the two models were similar, and the data was steady. The results of homogeneity analysis showed that the confidential intervals in all loops were crossed over with blank value; and direct and indirect estimates of the effects in network meta-analysis were not significantly different, with good homogeneity. ConclusionNetwork meta-analysis is a kind of indirect comparison analysis method, and its sensitivity is especially important. The introduction of homogeneity makes network meta-analysis more accurate. Using R software for sensitivity and homogeneity analysis in network meta-analysis is a feasible method.
ObjectiveTo introduce the method of meta-analysis for effect combination of regression coefficient conducted with the metafor package in R software. MethodsBy using the data of a published meta-analysis as an example, the detailed process of meta-analysis for regression coefficient was presented with metafor package in R. ResultsThe results of meta-analysis conducted with metaphor package in R were the same as the published literature. ConclusionAs a completely free open source software for statistical analysis, R can conduct meta-analysis for effect combination of regression coefficient flexibly and precisely, and should be expanded in the future meta-analysis.
R software is a free and powerful statistical software, which has the functions of data processing and graphics drawing and is widely used in the meta-analysis. This article introduced detailed operation steps of rmeta package which is suitable for meta-analysis of binary data, and also can finish cumulative meta-analysis, draw standard summary plots, forest plot and funnel plot. In summary, the functions of rmeta package are simple and easy to mastery. There are some limitations of current version which need to be improved in the future.