Differences

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

--- news:news2014 [2021/11/25 09:32] – Wolfgang Viechtbauer
+++ news:news2014 [2023/05/09 06:36] – [2014-11-24: New Version Out (1.9-5)] Wolfgang Viechtbauer
@@ Line 9: / Line 9: @@
 ==== 2014-11-24: New Version Out (1.9-5) ====
-New version of the metafor package is out (version 1.9-5). Adds a bit of functionality and flexibility, corrects a few minor bugs, and includes some improvements to the ''[[https://wviechtb.github.io/metafor/reference/rma.mv.html|rma.mv()]]'' function. Full changelog can be found [[:updates_old#changes_in_version_19-5_2014-11-24|here]].
+New version of the metafor package is out (version 1.9-5). Adds a bit of functionality and flexibility, corrects a few minor bugs, and includes some improvements to the ''[[https://wviechtb.github.io/metafor/reference/rma.mv.html|rma.mv()]]'' function. Full changelog can be found [[:updates_old#version_19-5_2014-11-24|here]].
 One thing I am quite excited about is that the ''[[https://wviechtb.github.io/metafor/reference/rma.mv.html|rma.mv()]]'' function now makes use of the Cholesky decomposition in the optimization when there is a ''random = ~ inner | outer'' formula and ''struct="UN"''. This is numerically more stable than the old approach that avoided non-positive definite solutions by forcing the log-likelihood to be negative infinity in those cases (which creates sharp discontinuities in the likelihood surface). The old behavior can be restored with ''control = list(cholesky=FALSE)'', but I doubt that this would be needed.