It depends on what sort of weights you have, but one approach is to
construct a weighted covariance matrix and then run factanal() on it.
That's what svyfactanal() in the survey package does. The difficult part
is the tests: you need to specify the sample size, and in the presence of
weights it may not be clear what the right sample size is -- svyfactanal()
has four options, probably none of them is ideal.
-thomas
On Thu, Jan 10, 2013 at 5:36 AM, Virgile Capo-Chichi
<vcapochi...@gmail.com>wrote:
> hello there,
> I am trying to use a weight variable in a factor analysis but apparently
> the factanal command does not have a weight option. Any way to this? Thanks
> for your suggestions, V
>
> [[alternative HTML version deleted]]
>
> ______________________________________________
> R-help@r-project.org mailing list
> 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.
>
--
Thomas Lumley
Professor of Biostatistics
University of Auckland
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list
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.
