Version: 0.8-2 Date: 2016-12-23 Text: Version: 2016-12-23 Text: Update maintainer email Version: 0.8-1 Text: Version: 2016-09-06 Category: New features Text: mtc.deviance() for convenient access to deviance statistics and plots. Additional deviance statistics calculated. Version: 2016-09-06 Category: Bugfixes and improvements Text: Depend on rjags >= 4-0, as JAGS 4 features are being used. Version: 2016-09-06 Category: Bugfixes and improvements Text: Fix node-splitting models with down-weighted studies. Version: 2016-09-06 Category: Bugfixes and improvements Text: Additional sanity checking of input data. Version: 2016-09-06 Category: Bugfixes and improvements Text: More appropriate default limits on plotCovariateEffect. Version: 2016-09-06 Category: Bugfixes and improvements Text: Corrections to atrialFibrillation dataset. Version: 0.8 Date: 2016-03-01 Text: Version: 2016-03-01 Category: New features Text: Network meta-regression using study-level covariates. Shared, per-class, exchangeable, or unrelated coefficients. Version: 2016-03-01 Category: New features Text: Allow adjusting relative effects and rank probabilities to a specific covariate level. Plot treatment effects versus covariate levels. Version: 2016-03-01 Category: New features Text: Down-weighting (variance inflation or likelihood adjustment) of studies (e.g. for inclusion of lower quality evidence). Version: 2016-03-01 Category: New features Text: Add example datasets for new regression features, as well as examples for contrast-based data and rate data. Version: 2016-03-01 Category: New features Text: Improved model fit diagnostics including per-arm or per-study deviance. Version: 2016-03-01 Category: Removed features Text: Removed "write.mtc.network" function to write the deprecated GeMTC XML format, as most networks can't be saved in that format anyway. Version: 2016-03-01 Category: Bugfixes Text: Fixed degrees of freedom in ANOHE I^2 computations. Version: 0.7-1 Date: 2015-10-12 Text: Version: 2015-10-12 Text: Update for compatibility with JAGS 4.0 Version: 0.7 Date: 2015-09-09 Text: Version: 2015-09-09 Category: Removed features Text: Support for WinBUGS and OpenBUGS was removed due to their various problems (lack of portability, lack of support for selecting blocks from arrays, bugs in setting monitors, and the constant need to track minor differences in syntax between JAGS and BUGS). Version: 2015-09-09 Category: New features Text: Added binom/log (risk ratio) support. Version: 2015-09-09 Category: New features Text: Ability to generate n * n relative effects table, and to generate plots directly from the table, bypassing the time-consuming computation of the quantiles. Version: 2015-09-09 Category: New features Text: Added residual deviance statistics (replaces and improves upon the DIC previously computed by JAGS). Version: 2015-09-09 Category: New features Text: Example datasets are now standard R data, and can be accessed using the variables `depression', `parkinson', `thrombolytic', and `smoking'. Version: 2015-09-09 Category: Enhancements Text: Forest plots: allow treatment descriptions to be displayed instead of IDs. Version: 2015-09-09 Category: Enhancements Text: Network plot: make proportional line width optional. Version: 2015-09-09 Category: Enhancements Text: Additional validations to catch obvious data entry mistakes. Version: 2015-09-09 Category: Enhancements Text: Better safeguards for starting values, and alternative approach to baseline priors for scales without infinite support. Version: 2015-09-09 Category: Enhancements Text: The XML package is no longer required to install gemtc, and will be loaded only if needed to read/write legacy .gemtc XML files. Version: 0.6-2 Date: 2015-04-19 Text: Version: 2015-04-18 Category: New features Text: Network plot: line width is now proportional to the number of studies. Version: 2015-04-18 Category: Enhancements Text: Forest plots: new options 'draw.no.effect' and 'center.label'. See ?blobbogram for documentation. Version: 2015-04-18 Category: Enhancements Text: Better validation of network properties and more helpful reporting of validation failures. Version: 2015-04-18 Category: Enhancements Text: Prevent zero prior heterogeneity variance (because it causes JAGS errors). Version: 2015-04-18 Category: Enhancements Text: Clear error when asked to parse non-existant XML file. Version: 0.6-1 Date: 2014-12-12 Text: Version: 2014-12-12 Category: Enhancements Text: Use the '.Call' interface for C code Version: 2014-12-12 Category: Enhancements Text: Better detect invalid treatment names Version: 2014-12-12 Category: Enhancements Text: Better detect the likelihood / link Version: 2014-12-12 Category: Bugfixes Text: Fix node-splitting models in sparse networks (#31) Version: 0.6 Date: 2014-03-11 Text: Version: 2014-03-11 Category: New features Text: Customizable prior distribution for heterogeneity. The prior can be set on the standard deviation, variance, or precision. It can use any distribution supported by BUGS/JAGS. Informative priors for the log odds ratio (based on Turner et al. 2012) are also available. Version: 2014-03-11 Category: New features Text: Variance of the vague normal distributions for all other parameters can be controlled using 'om.scale'. By default it is still heuristically determined. Version: 2014-03-11 Category: New features Text: Change handling of 4+-arm trials in node-splitting models and ANOHE summary Version: 2014-03-11 Category: New features Text: Enable linearModel='fixed' for mtc.anohe() Version: 2014-03-11 Category: New features Text: Add literature references for various methods to gemtc-package Version: 2014-03-11 Category: New features Text: Add mtc.data.studyrow() to convert the one-study-per-row format often used in BUGS models to the one-arm-per-row format used by GeMTC Version: 2014-03-11 Category: Enhancements Text: Upgrade unit testing infrastructure to testthat >= 0.8 Version: 2014-03-11 Category: Enhancements Text: Move validation tests into testthat infrastructure Version: 2014-03-11 Category: Enhancements Text: Add regression test suite that tries all summaries and plots on all models to check whether they crash. Version: 2014-03-11 Category: Enhancements Text: General clean up of example and test data files Version: 2014-03-11 Category: Known issues Text: Models with relative-effect data from trials with 4 or more arms can't be run using WinBUGS or OpenBUGS (#28). This seems to be due to a BUGS-bug. A warning is produced, saying to use JAGS instead. Version: 2014-03-11 Category: Bugfixes Text: Fix empty first page on PDF output of some plots (#12) Version: 2014-03-11 Category: Bugfixes Text: Fix ordering of generated data / initial values in models for relative effect data (#21) Version: 2014-03-11 Category: Bugfixes Text: Fix generating node-splitting models for relative effect data (#22) Version: 2014-03-11 Category: Bugfixes Text: Fix mtc.nodesplit.comparisons getting confused when both relative effect and arm-based data are present (#25) Version: 2014-03-11 Category: Bugfixes Text: Fix duplicated parameters in UME models (#26) Version: 0.5-3 Date: 2014-02-08 Text: Version: 2013-02-08 Text: Fix incompatibility with igraph 0.7 Version: 2013-02-08 Text: Fix node-splitting model generation bug Version: 0.5-2 Date: 2013-12-03 Text: Version: 2013-12-02 Text: Remove Matrix dependency by not using the Matrix-dependent parts of igraph. Version: 2013-12-02 Text: Correctly use C99 "inline" facility Version: 0.5-1 Date: 2013-10-30 Text: Version: 2013-10-30 Category: Improvements Text: Converted several plots to use the standard R mechanism of asking for the next page, rather than our own hack. Version: 2013-10-30 Category: Improvements Text: The plot() for the summary() of mtc.anohe() now has a nicer default scale range. Version: 2013-10-30 Category: Improvements Text: Import Matrix package because of igraph changes. Version: 2013-10-30 Category: Bugfixes Text: mtc.anohe() mixed up treatments or studies in some extraordinary circumstances, due to automatic conversions to/from factor. Version: 2013-10-30 Category: Bugfixes Text: blobbogram() would crash when it could not find reasonable scales and none were specified. Version: 2013-10-30 Category: Bugfixes Text: blobbogram() created an empty first page when plotting to off-screen devices. Version: 2013-10-30 Category: Bugfixes Text: mtc.anohe() called sd() on a matrix, which is deprecated. Version: 2013-10-30 Category: Bugfixes Text: mtc.nodesplit() used "A vs B" for d.A.B instead of "B vs A" like the other plots. Version: 0.5 Date: 2013-09-24 Text: Version: 2013-09-24 Category: New features Text: node-splitting models Version: 2013-09-24 Category: New features Text: mtc.nodesplit() wrapper to run multiple node-splitting models Version: 2013-09-24 Category: New features Text: calculate DIC model fit (JAGS only) Version: 2013-09-24 Category: New features Text: add preferredDirection to rank.probability() Version: 2013-09-24 Category: New features Text: default plot() for rank.probability() Version: 0.4 Date: 2013-08-09 Text: Version: 2013-08-09 Category: New features Text: fixed effect models Version: 2013-08-09 Category: New features Text: poisson/log likelihood/link for survival data Version: 2013-08-09 Category: New features Text: allow std.err instead of std.dev + sampleSize in continuous data sets Version: 2013-08-09 Category: Changes Text: refuse to generate models when treatments are duplicated in multiple arms of the same study, since the code does not take this into account. Version: 2013-08-09 Category: Changes Text: network$data is now network$data.ab for consistency with network$data.re Version: 2013-08-09 Category: Changes Text: likelihood/link implementations can now define their data requirements Version: 2013-08-09 Category: Changes Text: export ll.call for programmatic access to likelihood/link specific functions Version: 2013-08-09 Category: Bugfixes Text: multi-arm trial decomposition sometimes resulted in NA standard errors Version: 2013-08-09 Category: Bugfixes Text: WinBUGS and OpenBUGS had complaints about the relative effect code Version: 2013-08-09 Category: Bugfixes Text: safer matrix indexing: explicit 'drop=' Version: 2013-08-09 Category: Bugfixes Text: safer data frame indexing: use [['x']] instead of $x Version: 0.3 Date: 2013-07-16 Text: Version: 2013-07-16 Category: Many additional features Text: support for relative effect data Version: 2013-07-16 Category: Many additional features Text: support for mixed arm-based and relative effect data Version: 2013-07-16 Category: Many additional features Text: binom/cloglog likelihood/link for rate data Version: 2013-07-16 Category: Many additional features Text: unrelated mean effects (UME) model Version: 2013-07-16 Category: Many additional features Text: unrelated study effects (USE) model Version: 2013-07-16 Category: Many additional features Text: analysis of heterogeneity with heterogeneity plot (EXPERIMENTAL) Version: 2013-07-16 Category: Many additional features Text: full access to generated code, data structures, and parameters Version: 2013-07-16 Category: Many additional features Text: guard against "impossible" initial values Version: 2013-07-16 Category: Also, bugfixes and documentation updates Text: Version: 0.2 Date: 2013-02-19 Text: Version: 2013-02-18 Category: Dropped Java dependency by rewriting core algorithms in R. Text: Remove dependency on rJava Version: 2013-02-18 Category: Dropped Java dependency by rewriting core algorithms in R. Text: Use own forest plot methods instead of meta package Version: 2013-02-18 Category: Dropped Java dependency by rewriting core algorithms in R. Text: Fix bug in rank.probabilities when only two treatments in network Version: 2013-02-18 Category: Dropped Java dependency by rewriting core algorithms in R. Text: Various bugfixes Version: 2013-02-18 Category: Dropped Java dependency by rewriting core algorithms in R. Text: Compatibility note: inconsistency models are no longer supported by this package Version: 2013-02-18 Category: Dropped Java dependency by rewriting core algorithms in R. Text: Compatibility note: the argument order of mtc.network has changed Version: 2013-02-18 Category: Dropped Java dependency by rewriting core algorithms in R. Text: Compatibility note: the YADAS sampler is no longer available Version: 0.1-2 Date: 2013-01-21 Text: Version: 2013-01-21 Category: Bugfix release. Addresses the following issues: Text: Correct the initial values generation for the random effects standard deviation parameter Version: 2013-01-21 Category: Bugfix release. Addresses the following issues: Text: Do not fail on relative.effect when saving and loading samples Version: 2013-01-21 Category: Bugfix release. Addresses the following issues: Text: Make Java open tab-completed paths Version: 2013-01-21 Category: Bugfix release. Addresses the following issues: Text: Use correct column name for continuous data Version: 2013-01-21 Category: Bugfix release. Addresses the following issues: Text: When only YADAS available, run YADAS by default Version: 0.1-1 Date: 2012-10-30 Text: Version: 2012-10-30 Text: Fix compatibility issue with Java on 32bit Mac OS X. Version: 0.1 Date: 2012-10-25 Text: Version: 2012-10-25 Category: First official release of the GeMTC R package. The package enables Text: Version: 2012-10-25 Category: Bayesian network meta-analysis (also known as MTC, Mixed Treatment Text: Version: 2012-10-25 Category: Comparisons) in R. Network meta-analysis models can be generated and Text: Version: 2012-10-25 Category: then run using MCMC software: JAGS (using the rjags package), OpenBUGS Text: (using the BRugs package), WinBUGS (using the R2WinBUGS package) or Version: 2012-10-25 Category: YADAS (provided by GeMTC). The GeMTC GUI can be used instead of or in Text: Version: 2012-10-25 Category: conjunction with the R package Text: