[R-meta] Results from the meta-regression

[Viechtbauer, Wolfgang (SP)]

Dear Tarun,

There is no element of randomness in rma(), so if you did not make any changes, the differences cannot come from the function itself.

Best,
Wolfgang

>-----Original Message-----
>From: R-sig-meta-analysis [mailto:r-sig-meta-analysis-bounces using r-project.org] On
>Behalf Of Tarun Khanna
>Sent: Tuesday, 23 February, 2021 22:04
>To: r-sig-meta-analysis using r-project.org
>Subject: [R-meta] Results from the meta-regression
>
>Dear All,
>
>I ran a meta regression using the rma and rma.mv function. The exact command is
>below:
>
>rma(yi=zi, vi = vi, method="REML", data = dfinc, test = "knha", mods = ~
>                         `Commitment strategies`+ Gamification+
>                          Randomisation + StatsMethod + StudyDesign +
>                          Weather +
>                          OptedIn + interventionTreatmentPeriod +
>                          Region + StudyYear )
>
>I re-ran the code again after a while and it seems that the results are slightly
>different. There are slight differences in the estimated coefficients and
>variances. As far as I can tell I didn't change the underlying data. Is it
>possible that results change because of the function that I am using here? Or must
>it be some change in the code or data?
>
>Best
>Tarun
>
>Tarun Khanna
>Research Associate
>
>Hertie School
>
>Friedrichstraße 180
>10117 Berlin ∙ Germany
>khanna using hertie-school.org ∙ www.hertie-school.org<http://www.hertie-school.org/>