http://spssx-discussion.165.s1.nabble.com/about-to-exploratory-factor-analysis-tp5435719p5436325.html
I can speak in particular to the question of factor analyses
of rating scales with a few dozen clinical items. - If your
data is other, please describe.
I've done a huge number of these over the years, and I
very seldom saw an item that failed to load at least 0.30
on at least one accepted factor. When that happened, it
was always clear, on inspection, that the item was "bad" -
mis-written, ambiguous, or irrelevant to the general theme
of the other items (even if it would be relevant elsewhere).
In that case, it was appropriate to drop the item explicitly, with
explanation, and to re-run the analysis.
If I had *many* dozens of items, or a different sort of items,
I think I would have to consider, mainly, what my written
explanation would be for dropping the items. How exploratory
is the whole study? How badly, or for what reason, do the
dropped items fail an "eyeball" test?
--
Rich Ulrich
> Date: Fri, 27 Jan 2012 07:33:10 -0500
> From:
[hidden email]> Subject: about to exploratory factor analysis
> To:
[hidden email]>
> Hi all,
>
> I have a question. Namely, running exploratory factor analysis (EFA) in spss,
> it gives explained variance proportion for each eiganvalue. Besides, the
> variables that have loading less than .30 can be dropped out from data set
> according to this analysis. Herein, reporting the total explained variance in
> articles, is it necessary or appropriate to repeat the EFA with reduced data
> set and report the total explained variance obtained from second analysis?
> thanks in advance
>
[...]