The factor score coefficient of a variable equals the loading of
the factor on the variable, divided by the factor's eigenvalue.
You do not need to add the coefficients multiplied by the variables
to obtain factor scores: they are automatically produced by SPSS with the
/SAVE subcommand: scores for all the extracted factors are saved to the
active file.
There is no limit to the number of variables you can include in the
analysis. But you may want to limit the number of factors you retain.
The first few factors probably load on many variables. Further
factors, especially those accounting for only a small proportion of total
variance, may be associated with only one (or perhaps only two or three) of
your many variables. This is because part of the variance of those variables
is not correlated with variance in most other variables. The common variance
is accounted for in common factors.
Hector
-----Original Message-----
From: SPSSX(r) Discussion [mailto:
[hidden email]] On Behalf Of
Rita Clivio
Sent: 20 September 2007 13:43
To:
[hidden email]
Subject: FACTOR ANALYSIS: SCORE COEFFICIENT MATRIX CALCULATION AND OTHERS
Hi all
We run factor analysis in spss and used the saved factor score .
Adding the standardized row variables multiplied for the
coefficient in
factor score coefficient, we obtain the factor score.
Does anyone know how is calculated the coefficient in the factor
score
coefficient matrix?
Other question: We have factors for which only one variables is
loaded.
Well, I have a very large number of variables.
There is a maximum number of variables in using factor analysis?
What do you
think about ? What do you suggest ?
Thanks in advance for your help
Rita
No virus found in this outgoing message.
Checked by AVG Free Edition.
Version: 7.5.487 / Virus Database: 269.13.25/1018 - Release Date:
19/09/2007
15.59
Locked
