R help - Nov 2015 - MAc-pakcage, on OS-X 10.11.1: Warning Message In sqrt(var.T.agg.tau) : NaNs produced

Hi there, 

I am trying to run a mini meta-analysis for three studies within one of my
papers. I am using the Mac package for meta-analyzing correlation coefficients.

I am using the following command: omni(es = z, var = var.z, data = dat,
type="weighted", method = "fixed", ztor = TRUE)

This produces the expected values, but also a warning message: In
sqrt(var.T.agg.tau) : NaNs produced

This message is repeated twice.

I am wondering how to interpret this error message. Is this because the program
can?t estimate certain parameters due to the small number of correlation
coefficients I am trying to analyze (only 3)?

Most importantly, can I report and interpret the output despite those messages? 

Kosta 
 


	[[alternative HTML version deleted]]

Dear Kostadin

You could give us the data (after all there are only three studies) so 
we can run it through a different package or you could look at the code 
for omni and see where it is computing sqrt(var.T.agg.tau) and how it 
computed that in the first place.

And you could turn off HTML in your mailer as otherwise your mail can 
get corrupted.

On 10/11/2015 08:14, Kostadin Kushlev wrote:
> Hi there,
>
> I am trying to run a mini meta-analysis for three studies within one of my
papers. I am using the Mac package for meta-analyzing correlation coefficients.
>
> I am using the following command: omni(es = z, var = var.z, data = dat,
type="weighted", method = "fixed", ztor = TRUE)
>
> This produces the expected values, but also a warning message: In
sqrt(var.T.agg.tau) : NaNs produced
>
> This message is repeated twice.
>
> I am wondering how to interpret this error message. Is this because the
program can?t estimate certain parameters due to the small number of correlation
coefficients I am trying to analyze (only 3)?
>
> Most importantly, can I report and interpret the output despite those
messages?
>
> Kosta
>
>
>
> 	[[alternative HTML version deleted]]
>
> ______________________________________________
> R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>
-- 
Michael
http://www.dewey.myzen.co.uk/home.html