Question

[<Omar Malik>]

Hello,

Does anyone know of any citations that support the use of regression factor
scores as composite measures of factors rather than using means of variables
or  sums of variables as measures of a factor?

Thanks in advance.

Omar R. Malik
Assistant Professor of Management
School of  Business Administration
Philadelphia University
School House Lane &  Henry Avenue
Philadelphia PA 19144
Tel: [phone]
Email:  [hidden email]




**************************************Check out AOL's list of 2007's hottest
products.
(http://money.aol.com/special/hot-products-2007?NCID=aoltop00030000000001)

=====================
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

[Alexander J. Shackman-2]

i would try looking in tabachnick & fidell, cohen cohen west & aiken (where
they discuss how to deal with multicolinearity), or maybe gorsuch's factor
analysis textbook

the approach you describe is related to discriminant analysis and
pca-regression (which is widely used in analytic chemistry).

the main reason for not doing what you suggest (& instead sticking with sum
or mean of z-transformed vars) is that (i) it will be difficult for others
to exactly replicate your results, and (ii) the factor scores may not be
stable if you have a small sample (<10 Ss x number of items)...there are
approaches (based on permutation) for dealing with the latter problem in the
dedicated pca-regression software packages, but most of them do not allow
you to rotate the solutions. you can experiment with them, s most have free
30 d demos.

hth, ajs

On Dec 4, 2007 7:29 PM, <Omar Malik> <[hidden email]> wrote:

> Hello,
>
> Does anyone know of any citations that support the use of regression
> factor
> scores as composite measures of factors rather than using means of
> variables
> or  sums of variables as measures of a factor?
>
> Thanks in advance.
>
> Omar R. Malik
> Assistant Professor of Management
> School of  Business Administration
> Philadelphia University
> School House Lane &  Henry Avenue
> Philadelphia PA 19144
> Tel: [phone]
> Email:  [hidden email]
>
>
>
>
> **************************************Check out AOL's list of 2007's
> hottest
> products.
> (http://money.aol.com/special/hot-products-2007?NCID=aoltop00030000000001)
>
> =====================
> 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
>

--
Alexander J. Shackman
Laboratory for Affective Neuroscience
Waisman Laboratory for Brain Imaging & Behavior
University of Wisconsin-Madison
1202 West Johnson Street
Madison, Wisconsin 53706

Telephone: [phone]
FAX: [phone]
EMAIL: [hidden email]
http://psyphz.psych.wisc.edu/~shackman
Calendar {still under construction}:
http://www.google.com/calendar/embed?src=ajshackman%40gmail.com

=====================
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