Timeline for Metafor package: Interpreting meta-regression model
Current License: CC BY-SA 3.0
4 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jun 11, 2020 at 14:32 | history | edited | CommunityBot |
Commonmark migration
|
|
| Jun 1, 2017 at 0:54 | comment | added | Fam | Thank you @Wolfgang! Your comments are most helpful. I am thinking of removing "mix" factor (studies who provide alpha for specific sample vs study who provide one alpha for multiple samples; ie one alpha for both clinical sample and healthy control group) since only 9 studies are using mixed sample. I will try to do the side-by-side analysis you suggested. It seems like a good idea! Thank you @mdewey! Dropping the two variables indeed improve the R2. The "PSS verison" has now become a significant moderator. I wonder if it is a "true" moderator... | |
| May 31, 2017 at 15:59 | comment | added | mdewey | Given that two of the variables with much missing are ecological I might try just dropping them and re-fitting with more studies. As you say, if the models give substantively different results the OP needs luck. | |
| May 31, 2017 at 15:35 | history | answered | Wolfgang | CC BY-SA 3.0 |