Principal Component Analysis

[rsling]

Recently I am doing Principal Component Analysis, and i read from some online material that ...

The first phase of principal component analysis was devoted to verifying that the following requirements were met:

1. The variables included must be metric level or dichotomous nominal level and the sample size must be greater than 50 (preferably 100)

2. The ratio of cases to variables must be 10 to 1 or larger

3. The correlation matrix for the variables better contain significant correlations and must has a determinant (R) of  0 ＜｜R︱＜1

4. The Bartlett’s test of sphericity is statistically significant and the size of the overall Kaiser-Meyer-Olkin (KMO) statistic must be 0.60 or above

5. Variables with measure of sampling adequacy (MSA) values below 0.60 must be removed

I have follow the above steps in the analysis, but when i am doing the writing up, I need formal referencing for the above "rules". It seems hard for me to find out the reference. Can anyone help me on that? Thanks a lot!

[SR Millis-3]

Try this:

Pett, M. A., Lackey, N. R., & Sullivan, J. J. (2003). Making sense of factor analysis: The use of factor analysis for instrument development in health care research. Thousand Oaks, CA: Sage Publications, Inc.


~~~~~~~~~~~
Scott R Millis, PhD, ABPP (CN,CL,RP), CStat, CSci
Professor & Director of Research
Dept of Physical Medicine & Rehabilitation
Dept of Emergency Medicine
Wayne State University School of Medicine
261 Mack Blvd
Detroit, MI 48201
Email:  [hidden email]
Email:  [hidden email]
Tel: [phone]
Fax: [phone]


--- On Thu, 11/19/09, rsling <[hidden email]> wrote:

> From: rsling <[hidden email]>
> Subject: Principal Component Analysis
> To: [hidden email]
> Date: Thursday, November 19, 2009, 10:51 PM
> Recently I am doing Principal
> Component Analysis, and i read from some online
> material that ...
>
> The first phase of principal component analysis was devoted
> to verifying
> that the following requirements were met:
>
> 1.�  �  �  The variables included must be
> metric level or dichotomous nominal level
> and the sample size must be greater than 50 (preferably
> 100)
>
> 2.�  �  �  The ratio of cases to variables must
> be 10 to 1 or larger
>
> 3.�  �  �  The correlation matrix for the
> variables better contain significant
> correlations and must has a determinant (R) of�  0
> ＜｜R︱＜1
>
> 4.�  �  �  The Bartlett’s test of sphericity
> is statistically significant and the
> size of the overall Kaiser-Meyer-Olkin (KMO) statistic must
> be 0.60 or above
>
> 5.�  �  �  Variables with measure of sampling
> adequacy (MSA) values below 0.60 must
> be removed
>
> I have follow the above steps in the analysis, but when i
> am doing the
> writing up, I need formal referencing for the above
> "rules". It seems hard
> for me to find out the reference. Can anyone help me on
> that? Thanks a lot!
> --
> View this message in context: http://old.nabble.com/Principal-Component-Analysis-tp26422295p26422295.html
> Sent from the SPSSX Discussion mailing list archive at
> Nabble.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
>

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

[Jonathan Drennan]

The following may also help:

Brown T. (2006)  Confirmatory Factor Analysis for Applied Research, Guilford Press, New York.

Costello A., Osborne J. (2005) Best practices in exploratory factor analysis: four recommendations for getting the most from your analysis. Practical Assessment Research & Evaluation, 10, (7) Available online: http://pareonline.net/getvn.asp?v=10&n=7

Fabrigar, L. R., Wegener, D. T., MacCallum, R. C., & Strahan, E. J. (1999). Evaluating the use of exploratory factor analysis in psychological research. Psychological Methods, 4, 272-299.

Henson R., Roberts J. (2006) Use of Exploratory Factor Analysis in Published Research: Common Errors and Some Comment on Improved Practice. Educational and Psychological Measurement. 66, 393-416. 

Preacher K., MacCallum R. (2003) Repairing Tom Swift’s electric factor analysis machine. Understanding Statistics. 2, (1), 13-43. 

Thompson, B., & Daniel, L. G. (1996). Factor analytic evidence for the construct validity of scores: A historical overview and some guidelines. Educational and Psychological Measurement, 56, 197-208.

Dr. Jonathan Drennan
Lecturer
UCD School of Nursing, Midwifery and Health Systems
University College Dublin
Belfield
Dublin 4

On 20 Nov 2009, at 03:51, rsling wrote:

Recently I am doing Principal Component Analysis, and i read from some online
material that ...

The first phase of principal component analysis was devoted to verifying
that the following requirements were met:

1.      The variables included must be metric level or dichotomous nominal level
and the sample size must be greater than 50 (preferably 100)

2.      The ratio of cases to variables must be 10 to 1 or larger

3.      The correlation matrix for the variables better contain significant
correlations and must has a determinant (R) of  0 ＜｜R︱＜1

4.      The Bartlett’s test of sphericity is statistically significant and the
size of the overall Kaiser-Meyer-Olkin (KMO) statistic must be 0.60 or above

5.      Variables with measure of sampling adequacy (MSA) values below 0.60 must
be removed

I have follow the above steps in the analysis, but when i am doing the
writing up, I need formal referencing for the above "rules". It seems hard
for me to find out the reference. Can anyone help me on that? Thanks a lot!
--
View this message in context: http://old.nabble.com/Principal-Component-Analysis-tp26422295p26422295.html
Sent from the SPSSX Discussion mailing list archive at Nabble.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