[R-meta] Quick question about multiple independent samples within one study

[Anna-Lena Schubert]

That's neat! LRT and AIC favor the first model, while BIC is somewhat
ambigious (probably given complexity). In that case, I'll probably stick
with the first model. Thanks again for your help, Wolfgang and James!

Am 13.12.2018 um 17:41 schrieb Viechtbauer, Wolfgang (SP):
> First: I forgot the 'struct="UN"' part, so:
>
> res1 <- rma.mv(yi, dat$V, mods = ~ var1var2 - 1, random = list(~ var1var2 | id, ~ 1 | study/id), struct="UN", data=dat$dat)
>
> One could consider various models here. Another one would indeed be:
>
> res2 <- rma.mv(yi, dat$V, mods = ~ var1var2 - 1, random = list(~ var1var2 | study, ~ var1var2 | id), struct=c("UN","UN"), data=dat$dat)
>
> ('~ var1var2 | study/id' does not currently work, but if 'id' is coded in the way I show below, then this is the same thing).
>
> As James mentioned, one could use LRTs to compare such models:
>
> anova(res1, res2)
>
> Best,
> Wolfgang
>
>> -----Original Message-----
>> From: Anna-Lena Schubert [mailto:anna-lena.schubert using psychologie.uni-
>> heidelberg.de]
>> Sent: Thursday, 13 December, 2018 17:25
>> To: Viechtbauer, Wolfgang (SP); r-sig-meta-analysis using r-project.org
>> Subject: Re: [R-meta] Quick question about multiple independent samples
>> within one study
>>
>> Yes, that's exactly what my design looks like -- and all levels are
>> incompletely crossed because there are only few studies with additional
>> samples or additional measures. Thanks again for the prompt response and
>> the great help! My final question (so I don't have to post again if I run
>> into the same situation in the future) would be why the random effect for
>> var1var2 only contains "id" and not "study/id"?
>>
>> Best,
>> Anna-Lena
>>
>> Am 13.12.2018 um 17:06 schrieb Viechtbauer, Wolfgang (SP):
>>
>> Ok, so if I understand (and remember correctly), then you will have two
>> rows for each level of 'id', one for the correlation cor(x1, y) and one
>> for the correlation cor(x2, y). And now you also have studies with
>> multiple (independent) samples. So, for example:
>>
>> study  id   var1var2   yi
>> -------------------------
>> 1      1    var1       .
>> 1      1    var2       .
>> 2      2    var1       .
>> 2      2    var2       .
>> 2      3    var1       .
>> 2      3    var2       .
>> 3      4    var1       .
>> 3      4    var2       .
>>
>> So, study 2 has 2 samples and hence 4 rows. That would actually be a
>> model with an additional level beyond what Konstantopoulos describes. So
>> you have studies, samples within studies, and then two estimates within
>> samples. Then I would go with:
>>
>> res <- rma.mv(yi, dat$V, mods = ~ var1var2 - 1, random = list(~ var1var2
>> | id, ~ 1 | study/id), data=dat$dat)
>>
>> Best,
>> Wolfgang
-- 
Signatur


      Dr. Anna-Lena Schubert

Postdoc at Section of Personality
Heidelberg University - Institute of Psychology

Hauptstraße 47-51
D-69117 Heidelberg Germany

Phone: +49 6221 54 7746
Mail: anna-lena.schubert using psychologie.uni-heidelberg.de
Web: http://www.psychologie.uni-heidelberg.de/ae/diff/diff/people-schubert.html


-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://stat.ethz.ch/pipermail/r-sig-meta-analysis/attachments/20181213/e67d6ed0/attachment-0001.html>

-------------- next part --------------
A non-text attachment was scrubbed...
Name: kddmmepglbacnamk.png
Type: image/png
Size: 25980 bytes
Desc: not available
URL: <https://stat.ethz.ch/pipermail/r-sig-meta-analysis/attachments/20181213/e67d6ed0/attachment-0001.png>