I have conducted several studies involving systematically the same continuous IVs in order to study their impact on my DV. In each study, I used the same multiple regression model to analyse the data, looking specifically on the beta slopes estimates. I would like to combine my data altogether by performing a meta-analysis on these beta slopes from these studies. I would be very grateful if you could share some insights regarding the (preferably free) software to use / package in R software / the way to do it… Thanks a lot !
The first idea that comes into my mind is:
if you have all the data, you can fit the data all together in a mixed model that is the same as your multiple regression model but adding "experiment" as a random factor.
In R you can fit mixed models with lmer.
Dear Wojciech,
Once you have all your betas and their standard deviations ready, you may follow the steps discussed by Wolfgang Viechtbauer in his article: "Conducting Meta-Analyses in R with the metafor", Journal of Statistical Software, August 2010, volume 36, Issue 3.
Hope this helps.
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Statistical Software
- R Statistical Package