The metafor Package

A Meta-Analysis Package for R

User Tools

Site Tools


todo

Differences

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

Link to this comparison view

Both sides previous revision Previous revision
todo [2019/05/05 16:35]
Wolfgang Viechtbauer
todo [2019/07/23 14:24] (current)
Wolfgang Viechtbauer [Some Additional Thoughts/Considerations]
Line 100: Line 100:
 ==== Some Additional Thoughts/​Considerations ==== ==== Some Additional Thoughts/​Considerations ====
  
-  * When I get the chance, I would like to spend some time examining to what extent using other math libraries speeds things up, especially for ''​rma.mv()''​ and large datasets. See, for example, this [[http://​www.brodrigues.co/​2014/​11/​11/​benchmarks-r-blas-atlas-rro/​|comparison of R with Atlas, R with OpenBLAS, and Revolution R Open]] for an illustration of what I am talking about here. Most of the heavy lifting in metafor in fact involves matrix algebra, so maybe some real gains could be obtained this way. But this is only relevant if you are dealing with relatively large datasets (in the meta-analytic context, anything beyond a couple hundred effect size estimates is //huge//!). Note: I added an entry to the tips section on [[tips:​speeding_up_model_fitting|Speeding Up Model Fitting]] that addresses this issue to some extent.+  * When I get the chance, I would like to spend some time examining to what extent using other math libraries speeds things up, especially for ''​rma.mv()''​ and large datasets. Most of the heavy lifting in metafor in fact involves matrix algebra, so maybe some real gains could be obtained this way. But this is only relevant if you are dealing with relatively large datasets (in the meta-analytic context, anything beyond a couple hundred effect size estimates is //huge//!). Note: I added an entry to the tips section on [[tips:​speeding_up_model_fitting|Speeding Up Model Fitting]] that addresses this issue to some extent.
  
   * Alternatively,​ consider writing some of the slower parts directly in C++ (via [[http://​cran.r-project.org/​web/​packages/​Rcpp/​index.html|Rccp]];​ see also [[ http://​rcpp.org/​]] and [[http://​adv-r.had.co.nz/​Rcpp.html]]).   * Alternatively,​ consider writing some of the slower parts directly in C++ (via [[http://​cran.r-project.org/​web/​packages/​Rcpp/​index.html|Rccp]];​ see also [[ http://​rcpp.org/​]] and [[http://​adv-r.had.co.nz/​Rcpp.html]]).
todo.txt ยท Last modified: 2019/07/23 14:24 by Wolfgang Viechtbauer