On Thu, 26 Jun 2008 11:06:37 +1000, MCLAREN, Donald
<[log in to unmask]> wrote:
<snip>
>The Fischer Z transform is not a Z-statistic, but rather the normalized
form
>of the correlation coefficent (r). As such, it is independent of scaling
and
>passing it to the second level is the same as passing the normalized
betas.
>Thus, its still a random-effects analysis or mixed-effects depending on
the
>terminology. It is not a fixed effects though.
I highly doubt that passing normalized betas leads to a valid random
effects analysis, if by "normalized betas" you mean standardized
regression coefficients, a la
http://en.wikipedia.org/wiki/Standardized_coefficient
Of course, one issue (particularly germane to the case of correlation
coefficients) is what coefficient the putative random effects analysis is
actually trying to deal with.
<snip>
|