The metafor Package

A Meta-Analysis Package for R

User Tools

Site Tools


news:news2015

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision
Previous revision
news:news2015 [2021/11/25 09:30] Wolfgang Viechtbauernews:news2015 [2023/05/09 06:39] (current) – [2015-05-07: New Version Out (1.9-6)] Wolfgang Viechtbauer
Line 11: Line 11:
 ==== 2015-09-28: New Version Out (1.9-8) ==== ==== 2015-09-28: New Version Out (1.9-8) ====
  
-A new version of the package is up on [[https://cran.r-project.org/web/packages/metafor/index.html|CRAN]] now. The most interesting changes from my perspective are the addition of the ''[[https://wviechtb.github.io/metafor/reference/robust.html|robust()]]'' function for obtaining (cluster) robust tests and confidence intervals for ''rma.uni'' and ''rma.mv'' models (along the lines of the Eicker-Huber-White method) and that ''[[https://wviechtb.github.io/metafor/reference/confint.rma.html|confint()]]'' now works for models fitted with the ''[[https://wviechtb.github.io/metafor/reference/rma.mv.html|rma.mv()]]'' function (providing profile likelihood confidence intervals for variance components and correlation parameters). Full changelog can be found [[:updates#changes_in_version_19-8_2015-05-28|here]].+A new version of the package is up on [[https://cran.r-project.org/web/packages/metafor/index.html|CRAN]] now. The most interesting changes from my perspective are the addition of the ''[[https://wviechtb.github.io/metafor/reference/robust.html|robust()]]'' function for obtaining (cluster) robust tests and confidence intervals for ''rma.uni'' and ''rma.mv'' models (along the lines of the Eicker-Huber-White method) and that ''[[https://wviechtb.github.io/metafor/reference/confint.rma.html|confint()]]'' now works for models fitted with the ''[[https://wviechtb.github.io/metafor/reference/rma.mv.html|rma.mv()]]'' function (providing profile likelihood confidence intervals for variance components and correlation parameters). Full changelog can be found [[:updates_old#version_19-8_2015-05-28|here]].
  
 ==== 2015-09-26: More Than 1000 Citations ==== ==== 2015-09-26: More Than 1000 Citations ====
Line 19: Line 19:
 ==== 2015-05-22: New Version Out (1.9-7) ==== ==== 2015-05-22: New Version Out (1.9-7) ====
  
-Had to update the package due to some tests failing on Sparc Solaris. As far as I can tell, the issue seems to be resolved now (see the [[http://cran.r-project.org/web/checks/check_results_metafor.html|CRAN Package Check Results]]). Also, after some extensive testing, I decided to change the default optimizer for ''[[https://wviechtb.github.io/metafor/reference/rma.mv.html|rma.mv()]]'' from ''optim()'' with ''"Nelder-Mead"'' to ''nlminb()''. This is in principle a non-backwards compatible change, which I am not crazy about doing, but really a necessary one. Extensive testing indicated that ''nlminb()'' (and also ''optim()'' with ''"BFGS"'') is typically quicker and more robust than the implementation of the Nelder-Mead algorithm in ''optim()''. Full changelog [[:updates_old#changes_in_version_19-7_2015-05-22|here]].+Had to update the package due to some tests failing on Sparc Solaris. As far as I can tell, the issue seems to be resolved now (see the [[http://cran.r-project.org/web/checks/check_results_metafor.html|CRAN Package Check Results]]). Also, after some extensive testing, I decided to change the default optimizer for ''[[https://wviechtb.github.io/metafor/reference/rma.mv.html|rma.mv()]]'' from ''optim()'' with ''"Nelder-Mead"'' to ''nlminb()''. This is in principle a non-backwards compatible change, which I am not crazy about doing, but really a necessary one. Extensive testing indicated that ''nlminb()'' (and also ''optim()'' with ''"BFGS"'') is typically quicker and more robust than the implementation of the Nelder-Mead algorithm in ''optim()''. Full changelog [[:updates_old#version_19-7_2015-05-22|here]].
  
 ==== 2015-05-07: New Version Out (1.9-6) ==== ==== 2015-05-07: New Version Out (1.9-6) ====
Line 28: Line 28:
   - The various ''[[https://wviechtb.github.io/metafor/reference/profile.rma.html|profile()]]'' functions now can do parallel (multicore) processing (which is especially relevant for ''rma.mv'' objects, where profiling is crucial and model fitting can be slow).   - The various ''[[https://wviechtb.github.io/metafor/reference/profile.rma.html|profile()]]'' functions now can do parallel (multicore) processing (which is especially relevant for ''rma.mv'' objects, where profiling is crucial and model fitting can be slow).
  
-There are of course a number of additional changes and improvements to the package -- the full changelog can be found [[:updates_old#changes_in_version_19-6_2015-05-07|here]].+There are of course a number of additional changes and improvements to the package -- the full changelog can be found [[:updates_old#version_19-6_2015-05-07|here]].
  
 ==== 2015-05-04: To-Do List / Planned Features ==== ==== 2015-05-04: To-Do List / Planned Features ====
news/news2015.txt · Last modified: 2023/05/09 06:39 by Wolfgang Viechtbauer