Message-ID: <alpine.DEB.2.20.1908031737270.362@wvx1>
Date: 2019-08-03T15:45:50Z
From: Wolfgang Viechtbauer
Subject: [R-meta] metafor::rma-function: Statistically significant interaction, but increased tau2 – and how to get the slope from the output
In-Reply-To: <AM0PR08MB3681BAE732C319D38B08119DDCD90@AM0PR08MB3681.eurprd08.prod.outlook.com>
Thanks for the feedback. Ok, then the last model is overparameterized, but
this model:
rma.mv(logOR, logOR.var, mods = ~ CF1_Women..IMP,
random = ~ CF1_Women..IMP | id, struct="GEN", data=d)
(i.e., random intercepts and slopes for the different meta-analyses)
should be fine. But I understand your preference for sticking to the
protocol and using fixed effects for meta-analyses and the interactions is
also fine.
Best,
Wolfgang
On Fri, 2 Aug 2019, Sabrina Mai Nielsen wrote:
> Thanks a lot for very fast response!
>
> 1) Ok, I am happy to hear that it is a known issue and not necessarily
> caused by errors in my coding.
>
> 2) Perfect, that makes sense. Thanks a lot for making that clear for me.
>
> 3) Thanks a lot for the suggestions - I will try those models out! For
> my study, however, I have already protocolized the model I am using, so
> I may have to stick with that. - For the model that allows tau^2 to be
> different for every level of id, I do get the same as with the 'subset'
> model, as you said - cool! - The multilevel model adding random effects
> for meta-analyses was definitely among our considerations, however, we
> found it rather complex (e.g. by resulting in two variance components,
> sigma^2.1 and sigma^2.2) and we ended up choosing fixed effects for
> meta-analyses. - The profile plots are peaking nicely for the two first
> plots (?^2 and tau1^2), but not for the last two plots.
>
> Thanks again
>
> Best,
> Sabrina