Why do they differ so much? I've used fixed effects in both
A total of k=8 studies were included in the analysis. The observed log risk ratios ranged from -1.5404 to 0.0000, with the majority of estimates being negative (62%). The estimated average log risk ratio based on the fixed-effects model was \hat{\theta} = -0.8472 (95% CI: -1.2507 to -0.4438). Therefore, the average outcome differed significantly from zero (z = -4.1162, p < 0.0001).
According to the Q-test, there was no significant amount of heterogeneity in the true outcomes (Q(7) = 4.3450, p = 0.7393, I² = 0.0000%).
An examination of the studentized residuals revealed that none of the studies had a value larger than ± 2.7344 and hence there was no indication of outliers in the context of this model. According to the Cook's distances, one study (Wen et al., 2018 [16]) could be considered to be overly influential.
Neither the rank correlation nor the regression test indicated any funnel plot asymmetry (p = 0.5484 and p = 0.3286, respectively).
Why do JAMOVI MAJOR results hugely differ from RevMan?
Why do JAMOVI MAJOR results hugely differ from RevMan?
- Attachments
-
- RevMan fever incidence.PNG (28.33 KiB) Viewed 8383 times
Re: Why do JAMOVI MAJOR results hugely differ from RevMan?
I think I figured it out. It is because its log risk ratio while in Revman its not log risk ratio. I just don't get why jamovi uses log. There is only an option to remove log with odds ratio not risk ratio. And even if I chose odds ratio un-log option it only does this with the stats and not the forest plot.
Is there any chance someone could provide a code to remove log from the forest plot?
Is there any chance someone could provide a code to remove log from the forest plot?
Re: Why do JAMOVI MAJOR results hugely differ from RevMan?
I also figured out what estimator RevMan uses: Dersimonean & Laird (DL) whilst I've read a couple of studies which say Restricted Maximum Likelihood is superior to DL. Cool! Now I really want to ditch RevMan. However, I do really like the forest plots from Revman. Someone recreated them in Metafor: https://www.metafor-project.org/doku.php/plots:forest_plot_revman
Super cool but my R knowledge is next to none (I know python only and some matlab). Is there somewhere in jamovi where I can more or less copy paste this code (with some alterations I imagine) to overwrite the one that MAJOR uses? I can't seem to find where this package is to see if I can edit the code sufficiently
Super cool but my R knowledge is next to none (I know python only and some matlab). Is there somewhere in jamovi where I can more or less copy paste this code (with some alterations I imagine) to overwrite the one that MAJOR uses? I can't seem to find where this package is to see if I can edit the code sufficiently
Re: Why do JAMOVI MAJOR results hugely differ from RevMan?
Hey @apavlo,apavlo wrote:However, I do really like the forest plots from Revman. Someone recreated them in Metafor: https://www.metafor-project.org/doku.ph ... lot_revman
I'm in MAJOR, but not yet available in the jamovi library. At the moment I am away from my PC, but in September after a further check for possible problems, a PR will be started.
Cheers,
Maurizio
Re: Why do JAMOVI MAJOR results hugely differ from RevMan?
That would be amazing if this was added. However team is pushing for publication so september will be too late for the work I am doing at the moment. I've now managed to implement the forest plot in R. Unfortunately I can only create Revman forest plots for OR or RR not for mean difference. It becomes too technically difficult for me to modify the example code for mean differences forest plot... Oh well....
Re: Why do JAMOVI MAJOR results hugely differ from RevMan?
For clinical practitioners is very common to analyse Risk Ratio measured outcomes. Working with dichotomous variables the meta-analysis often is show with RR, but never log-RR.
Would be amazing to find a not-log-RR option (and OR) in Jamovi.
Would be amazing to find a not-log-RR option (and OR) in Jamovi.