Differences

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

--- tips:rma_vs_lm_lme_lmer [2016/07/01 17:25] – external edit 127.0.0.1
+++ tips:rma_vs_lm_lme_lmer [2021/04/16 07:50] – [S-Plus Version of lme()] Wolfgang Viechtbauer
@@ Line 285: / Line 285: @@
 These are the exact same results as obtained earlier with the ''rma()'' function. Unfortunately, the R version of the ''nlme'' package does not provide this functionality.
-**Update:** The R version of the ''nlme'' package //does// allow the use of the ''lmeControl(sigma = 1)'' control argument (this was added in version 3.1-123, which was released 2016-01-17). However, using this does not yield the same results as obtained above (the results are close but not the same). The results given above have also been compared to those obtained with Stata (metareg command) and SAS (proc mixed) and are definitely correct. This issue has also been raised on the R-sig-ME mailing list ([[https://stat.ethz.ch/pipermail/r-sig-mixed-models/2016q2/024862.html|see here]]).
+**Update:** The R version of the ''nlme'' package //does// allow the use of the ''lmeControl(sigma = 1)'' control argument (this was added in version 3.1-123, which was released 2016-01-17). However, using this does not yield the same results as obtained above (the results are close but not the same). The results given above have also been compared to those obtained with Stata (metareg command) and SAS (proc mixed) and are definitely correct. This issue has also been raised on the R-sig-ME mailing list ([[https://stat.ethz.ch/pipermail/r-sig-mixed-models/2016q2/024862.html|see here]]). See also this [[https://www.jepusto.com/bug-in-nlme-with-fixed-sigma/|blog post]] by James Pustejovsky for some further comparisons between ''lme()'' and the ''rma()'' and ''rma.mv()'' functions.
 ==== Summary ====