Dear Lily Wan,
Promax is an oblique rotation method and in that case the loadings in
the pattern matrix are standardized regression coefficients. These can,
occasionally, when there exists a strong multicollinearity, become
greater than 1 or smaller than -1. So the variable in question is
probably loading high on more than one factor. Perhaps it should be
drawn out of the analysis?
Best,
Henrik
Quoting Hong Wan <
[hidden email]>:
> Dear All
>
> I used Principal Component Analysis with Promax rotation. There were
> 23 items, and rotation converged in 6 iterations.
>
> How can I explain the loading which was greater than 1 in the pattern matrix?
>
> Thanks very much!
>
> Best wishes
>
> Yours sincerely,
> Lily Wan
>
> =====================
> 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
>
************************************************************
Henrik Lolle
Department of Economics, Politics and Public Administration
Aalborg University
Fibigerstraede 1
9220 Aalborg
Phone: (+45) 99 40 81 84
************************************************************
=====================
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