Recall that most uses of factor analysis operate on
the correlation matrix. Often the scaling of behavioral and
social science variables is arbitrary so factoring based
on covariances is not needed.
In many instances, it would not be problematic to factor items with
different response scales.
What is the nature of your data? What are you thinking of using
factor analysis to achieve?
Art Kendall
Social Research Consultants
On 11/13/2011 6:05 AM, abdalla alsmadi wrote:
Hi
is it ok to run the factor analysis if the items have
diferents scoring scale 1-4 1-5 1-9 ?
what are your suggestions??
thanks a lot
abdalla alsmadi
=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD
Art Kendall
Social Research Consultants
Locked
