[Rsiena-help] Threshold bound in meta-analysis

[Ruth M. Ripley]

Sara,

It is only possible to specify one bound, but you could run the meta 
analysis more than once with different bounds and keep the relevant parts 
of each output.

Regards,

Ruth

On Wed, 7 Mar 2012, Geven, S.A.J. (Sara) wrote:

> Dear all,
> 
> I am trying to run a meta-analysis in Rsiena, however my 'average similarity effect' is
> not estimated since none of the standard errors are below the threshold of 5.
> In the Rsiena manual I read that the standard errors for this effect tend to be larger
> and that therefore
> a larger threshold is appropiate. I know that with the 'bound' option you can change the
> threshold for inclusion for all the effects in your model. I was wondering whether it is
> also possible to only change the threshold of one effect, and if so whether it is
> advisable to do so.
> 
> Thank you in advance.
> 
> Kind regards,
> 
> Sara
> 
> 
>