R help - Dec 2013 - How do I print predicted effect sizes in forest plot?

Hi,

I am struggling a bit with creating a forest plot containing the predicted
effect size. As seen in other studies these effect sizes are shown per study
usually as a light grey diamond - which is what I want to achieve.

The calls I use are:
iat_result = rma(yi=Mean, vi=Variance_rounded, ni=N, sei=Std_error,
slab=Study_Name, subset=(Country == "AUT"), data=cma_iat,
method="HS")

summary.rma(iat_result)


#not sure how to use it or if needed
#predict(iat_result)

forest(iat_result)


At the end I am getting the forest plot as is without the predicted values. 

I am not sure if I need the predict function and how to use it? - the predict
function deliveres the same values as already computed in the rma object.


I checked the manual for package metafor but was not able to find out how to
print the predicted values per study.


kind regards, Alma
	[[alternative HTML version deleted]]

The model you are fitting is a random-effects model and does not include any
potential moderators/covariates. Therefore, the estimated intercept of that
model is *the* estimated/predicted (average) effect and it applies to each
study. That is why the predict function also just gives you that value. That
value is also included in the forest plot (at the bottom). The predicted
(average) effect will no longer be the same for each study only if you include
covariates in the model.

Best,
Wolfgang

--   
Wolfgang Viechtbauer, Ph.D., Statistician   
Department of Psychiatry and Psychology   
School for Mental Health and Neuroscience   
Faculty of Health, Medicine, and Life Sciences   
Maastricht University, P.O. Box 616 (VIJV1)   
6200 MD Maastricht, The Netherlands   
+31 (43) 388-4170 | http://www.wvbauer.com   
> -----Original Message-----
> From: r-help-bounces at r-project.org [mailto:r-help-bounces at
r-project.org]
> On Behalf Of Alma Wilflinger
> Sent: Thursday, December 05, 2013 22:06
> To: R help <r-help at r-project.org>
> Subject: [R] How do I print predicted effect sizes in forest plot?
> 
> Hi,
> 
> I am struggling a bit with creating a forest plot containing the predicted
> effect size. As seen in other studies these effect sizes are shown per
> study usually as a light grey diamond - which is what I want to achieve.
> 
> The calls I use are:
> iat_result = rma(yi=Mean, vi=Variance_rounded, ni=N, sei=Std_error,
> slab=Study_Name, subset=(Country == "AUT"), data=cma_iat,
method="HS")
> 
> summary.rma(iat_result)
> 
> 
> #not sure how to use it or if needed
> #predict(iat_result)
> 
> forest(iat_result)
> 
> 
> At the end I am getting the forest plot as is without the predicted
> values.
> 
> I am not sure if I need the predict function and how to use it? - the
> predict function deliveres the same values as already computed in the rma
> object.
> 
> 
> I checked the manual for package metafor but was not able to find out how
> to print the predicted values per study.
> 
> 
> kind regards, Alma
> 	[[alternative HTML version deleted]]

One more thing ... You used the command:

iat_result = rma(yi=Mean, vi=Variance_rounded, ni=N, sei=Std_error,
slab=Study_Name, subset=(Country == "AUT"), data=cma_iat,
method="HS")

This probably does not do what you want it to do. First of all, if you specify
vi, there is no need to specify sei (or vice-versa). One is sufficient. But more
crucially, I assume 'Mean' is what it says it is - a mean of a certain
variable X. And I assume that 'Variance_rounded' is the variance of said
variable X. But vi is used to specify the *sampling variance* of yi (or sei is
used to specify the standard error), which, for a mean, is the variance divided
by N (and the standard error is the SD divided by the square root of N):

http://en.wikipedia.org/wiki/Standard_error_of_the_mean#Standard_error_of_the_mean

So, my hunch is that you are not supplying the right information to the rma()
function.

Best,
Wolfgang 
> -----Original Message-----
> From: r-help-bounces at r-project.org [mailto:r-help-bounces at
r-project.org]
> On Behalf Of Alma Wilflinger
> Sent: Thursday, December 05, 2013 22:06
> To: R help <r-help at r-project.org>
> Subject: [R] How do I print predicted effect sizes in forest plot?
> 
> Hi,
> 
> I am struggling a bit with creating a forest plot containing the predicted
> effect size. As seen in other studies these effect sizes are shown per
> study usually as a light grey diamond - which is what I want to achieve.
> 
> The calls I use are:
> iat_result = rma(yi=Mean, vi=Variance_rounded, ni=N, sei=Std_error,
> slab=Study_Name, subset=(Country == "AUT"), data=cma_iat,
method="HS")
> 
> summary.rma(iat_result)
> 
> 
> #not sure how to use it or if needed
> #predict(iat_result)
> 
> forest(iat_result)
> 
> 
> At the end I am getting the forest plot as is without the predicted
> values.
> 
> I am not sure if I need the predict function and how to use it? - the
> predict function deliveres the same values as already computed in the rma
> object.
> 
> 
> I checked the manual for package metafor but was not able to find out how
> to print the predicted values per study.
> 
> 
> kind regards, Alma
> 	[[alternative HTML version deleted]]

At 21:05 05/12/2013, Alma Wilflinger wrote:
>Hi,
>
>I am struggling a bit with creating a forest plot containing the 
>predicted effect size. As seen in other studies these effect sizes 
>are shown per study usually as a light grey diamond - which is what 
>I want to achieve.
>
>The calls I use are:
>iat_result = rma(yi=Mean, vi=Variance_rounded, ni=N, sei=Std_error, 
>slab=Study_Name, subset=(Country == "AUT"), data=cma_iat,
method="HS")
Alma
You do not need to specify both vi and sei as one is sufficient and 
you do not need ni as well.
I realise that is not the question you asked (which Wolfgang has 
already answered).

>summary.rma(iat_result)
>
>
>#not sure how to use it or if needed
>#predict(iat_result)
>
>forest(iat_result)
>
>
>At the end I am getting the forest plot as is without the predicted values.
>
>I am not sure if I need the predict function and how to use it? - 
>the predict function deliveres the same values as already computed 
>in the rma object.
>
>
>I checked the manual for package metafor but was not able to find 
>out how to print the predicted values per study.
>
>
>kind regards, Alma
>         [[alternative HTML version deleted]]
Michael Dewey
info at aghmed.fsnet.co.uk
http://www.aghmed.fsnet.co.uk/home.html