A Meta-Analysis Package for R https://metafor-project.org/ 2026-07-10T17:40:41+00:00 https://metafor-project.org/ https://metafor-project.org/lib/exe/fetch.php/wiki:logo.png text/html 2026-06-21T19:02:34+00:00 Wolfgang Viechtbauer (wviechtb@undisclosed.example.com) https://metafor-project.org/doku.php/plots:forest_plot_orchard_style?rev=1782068554 Forest Plot in Orchard Style Description When dealing with large meta-analytic datasets, standard forest plots can become become excessively large (or the size of the elements in the plot become very small). To handle this problem, authors sometimes use forest-like plots that do not show the individual effect size estimates but instead the pooled estimate, often within the levels of a categorical moderator. However, as noted by Nakagawa et al. (2021), showing the individual estimates can still… text/html 2026-06-18T11:00:34+00:00 Wolfgang Viechtbauer (wviechtb@undisclosed.example.com) https://metafor-project.org/doku.php/plots:forest_plot_with_grouped_estimates?rev=1781780434 Forest Plot with Grouped Estimates Description When dealing with large meta-analytic datasets where studies may contribute multiple effect size estimates to the same analysis, standard forest plots can become excessively large (or the size of the elements in the plot become very small). One possible solution to this problem is to group the estimates from the same study together, omitting the text annotations (i.e., the estimate and corresponding confidence interval bounds) for the individual e… text/html 2026-04-27T09:14:20+00:00 Wolfgang Viechtbauer (wviechtb@undisclosed.example.com) https://metafor-project.org/doku.php/news:news?rev=1777281260 Package News 2026-06-21: Forest Plot in Orchard Style Another way to deal with large meta-analytic datasets is to draw so-called ‘orchard plots’. In contrast to standard forest plots, the estimates are shown without their corresponding CI bounds in a bee swarm style around the pooled estimate, with the pooled estimate superimposed on the points (with 95% CI/PI bounds). Often, the estimates are then grouped by some categorical moderator of interest. An example of such a plot is shown $\tau^2$… text/html 2026-04-27T08:30:41+00:00 Wolfgang Viechtbauer (wviechtb@undisclosed.example.com) https://metafor-project.org/doku.php/news:news2025?rev=1777278641 Package News for 2025 2025-09-20: 20,000+ Citations for the JSS Paper In 2010, I published a paper about the metafor package in the Journal of Statistical Software (Viechtbauer, 2010). I have been fortunate enough that users of the package have been quite diligent in citing the package in their papers. Today another milestone was reached, with the paper being cited $R^2$ text/html 2026-04-27T08:20:40+00:00 Wolfgang Viechtbauer (wviechtb@undisclosed.example.com) https://metafor-project.org/doku.php/tips:random_effects_mh_method?rev=1777278040 The 'Random-Effects Mantel-Haenszel Method' in Cochrane Reviews The Mantel-Haenszel method is an approach for fitting meta-analytic equal-effects models when dealing with studies providing data in the form of 2x2 tables or in the form of event counts (i.e., person-time data) for two groups (Mantel & Haenszel, 1959). The method is particularly advantageous when aggregating a large number of studies with small sample sizes (the so-called sparse data or increasing strata case).$\tau^2$$\tau^2$$$\h…