[R-meta] Time as indicator vs time as meaning

Stefanou Revesz @te|@noureve@z @end|ng |rom gm@||@com
Sun Oct 10 23:28:46 CEST 2021


Resending Model 2:

#***********************
MODEL 2:
#***********************
rma.mv(yi ~ time_btw + time_wthn, vi,
               random =
                 list(~ time_wthn | study, ~time_wthn | study), struct
= c("GEN","CAR"),data=data)

Variance Components:

outer factor: study      (nlvls = 49)
inner term:   ~time_wthn (nlvls = 9)

            estim    sqrt  fixed  rho:    intr  tm_w
intrcpt    0.4034  0.6351     no             -    no
time_wthn  0.1141  0.3377     no        1.0000     -

outer factor: study     (nlvls = 49)
inner factor: time_wthn (nlvls = 9)

            estim    sqrt  fixed
gamma^2    0.0770  0.2775     no
phi        0.0000             no

Model Results:

           estimate      se    zval    pval    ci.lb   ci.ub
intrcpt      0.1155  0.1861  0.6204  0.5350  -0.2493  0.4802
time_btw     0.3184  0.1815  1.7540  0.0794  -0.0374  0.6741    .
time_wthn    0.3247  0.0658  4.9344  <.0001   0.1957  0.4536  ***

On Sun, Oct 10, 2021 at 4:24 PM Viechtbauer, Wolfgang (SP)
<wolfgang.viechtbauer using maastrichtuniversity.nl> wrote:
>
> >-----Original Message-----
> >From: Stefanou Revesz [mailto:stefanourevesz using gmail.com]
> >Sent: Sunday, 10 October, 2021 23:03
> >To: Viechtbauer, Wolfgang (SP)
> >Cc: R meta
> >Subject: Re: [R-meta] Time as indicator vs time as meaning
> >
> >ATTACHMENT(S) REMOVED: image.png
> >
> >Thanks! Reporting back the results for two models (note: "time_wk" =
> >"time_meaning_wks").
> >In model 1,  I used "time_wk" to the left of | for "CAR".
> >In model 2, I used "time_whtn" to the left of | for "CAR".
> >In both models, rho is estimated to be 1. But the likelihood profile
> >for rho seems ok for both models (attached).
> >
> >However, in model 1, phi is estimated to be 0.1170. In model 2, phi is
> >estimated to be 0. In both models, the likelihood profiles for phi
> >seem ok.
> >Which phi, then, seems appropriate?
> >
> >Thank you,
> >Stefanou
> >
> >#******************************
> >MODEL 1:
> >#******************************
> >rma.mv(yi ~ time_btw + time_wthn, vi,
> >               random =
> >         list(~ time_wthn | study, ~time_wk | study), struct =
> >c("GEN","CAR"),data=data)
> >
> >Variance Components:
> >
> >outer factor: study    (nlvls = 49)
> >inner term:   ~time_wk (nlvls = 12)
> >
> >          estim    sqrt  fixed  rho:    intr  tm_w
> >intrcpt  0.1306  0.3614     no             -    no
> >time_wk  0.0236  0.1536     no        1.0000     -
> >
> >outer factor: study   (nlvls = 49)
> >inner factor: time_wk (nlvls = 12)
> >
> >            estim    sqrt  fixed
> >gamma^2    0.0703  0.2652     no
> >phi        0.0544             no
> >
> >Model Results:
> >
> >           estimate      se    zval    pval    ci.lb   ci.ub
> >intrcpt      0.0049  0.1816  0.0272  0.9783  -0.3510  0.3608
> >time_btw     0.3399  0.2164  1.5708  0.1162  -0.0842  0.7641
> >time_wthn    0.2837  0.0708  4.0064  <.0001   0.1449  0.4224  ***
>
> Something doesn't match up here. The first part of the 'random' formula says '~ time_wthn | study' but the output says that the inner term is ~time_wk.
>
> >#******************************
> >MODEL 2:
> >#******************************
> >rma.mv(yi ~ time_btw + time_wthn, vi,
> >               random =
> >                 list(~ time_wthn | study, ~time_wthn | study), struct
> >= c("GEN","CAR"),data=data)
> >Variance Components:
> >
> >outer factor: study      (nlvls = 49)
> >inner term:   ~time_wthn (nlvls = 9)
> >
> >            estim    sqrt  fixed  rho:    intr  tm_w
> >intrcpt    0.4034  0.6351     no             -    no
> >time_wthn  0.1141  0.3377     no        1.0000     -
> >
> >outer factor: study     (nlvls = 49)
> >inner factor: time_wthn (nlvls = 9)
> >
> >            estim    sqrt  fixed
> >gamma^2    0.0770  0.2775     no
> >phi        0.0000             no
> >
> >Test for Residual Heterogeneity:
> >QE(df = 402) = 1450.3879, p-val < .0001
> >
> >Test of Moderators (coefficients 2:3):
> >QM(df = 2) = 24.4255, p-val < .0001
> >
> >Model Results:
> >
> >           estimate      se    zval    pval    ci.lb   ci.ub
> >intrcpt      0.1155  0.1861  0.6204  0.5350  -0.2493  0.4802
> >time_btw     0.3184  0.1815  1.7540  0.0794  -0.0374  0.6741    .
> >time_wthn    0.3247  0.0658  4.9344  <.0001   0.1957  0.4536  ***



More information about the R-sig-meta-analysis mailing list