Factor Analysis on Factors
Hi Everyone: Good to join this group. I am doing exploratory factor analysis on several measures related to human personality development. The resulting factors are interesting. I am wondering if it is possible to do a factor analysis on the factors themselves? In this way, I hope to cluster the factors into "mega factors" (Neurosis-Passivity; Narcissism-Aggression, etc.). I don't know much about confirmatory factor analysis. Would the latter yield this type of information (i.e., higher level factors)? Thanks for your help, -Charles ...

Factor Analysis: Number of Factors
Hi, I have a very basic question in factor analysis - how many factors to menti= on in nfactor option while running a proc factor I can select how many factors I want to analyze by checking the scree plot = or by help of eigen value (>1), but if I run proc factor with nfactor=3D10= or nfactor=3D50 then loading on factors changes significantly and this eve= n changes the business definition of my factors. Please help me understand how to choose the optimal value of nfactor or if = there is a way by which we derive that value than what is that way Regards, Rajat _______________________...

Re: Factor Analysis on Factors
charles19 <charles19@SYMPATICO.CA> wrote >Sent: Jun 26, 2008 9:43 AM >To: SAS-L@LISTSERV.UGA.EDU >Subject: Factor Analysis on Factors > >Hi Everyone: > >Good to join this group. We're a fun bunch. :-) Nice to have you I am doing exploratory factor analysis on >several measures related to human personality development. The >resulting factors are interesting. I am wondering if it is possible to >do a factor analysis on the factors themselves? In this way, I hope to >cluster the factors into "mega factors" (Neurosis-Passivity; >Narcissi...

Factor analysis: interpretation of factors
Hello, To gain more insight in 23 variables, I used factor analysis. The best solution was found using 9 factors. Looking at the factors, I found that it all made very good sense: it all looks right, except for 1 variable. I really can't explain his presence on the factor he's in. I tried what would happen when I used 10 factors, but he still remains on that factor. I don't think there is anyway to solve this problem, so I'll just have to it for granted. My question is, - when writing a researchpaper - how does one report such an situation? In books about data analy...

Factor Analysis-How many factors I need
I used the following statement for my Factor Analysis : ************************************************************ proc factor DATA=OUT.Baseline priors=smc msa preplot plot ROTATE=varimax SCREE; Var Quest1-quest21; Run; ******************************************************* Below is the part of the output: FACTOR ANALYSIS FOR 21 QUESTIONS IN base The FACTOR Procedure Initial Factor Method: Principal Factors Factor Pattern Factor1 Factor2 Quest1 0.45597 -0.19266 Quest2 0.66878 -0.24750 Quest...

Re: Factor Analysis: Number of Factors
Rajat, Take a look at: http://ssc.utexas.edu/consulting/answers/general/gen16.html HTH, Art -------- On Mon, 6 Jul 2009 06:38:31 -0500, Mathur, Rajat <Rajat.Mathur@DIAMONDCONSULTANTS.COM> wrote: >Hi, > >I have a very basic question in factor analysis - how many factors to mention in nfactor option while running a proc factor > >I can select how many factors I want to analyze by checking the scree plot or by help of eigen value (>1), but if I run proc factor with nfactor=10 or nfactor=50 then loading on factors changes significantly and this even changes the busines...

Re: Factor Analysis: Number of Factors #3
--- On Mon, 7/6/09, Peter Flom <peterflomconsulting@MINDSPRING.COM> wrote: > From: Peter Flom <peterflomconsulting@MINDSPRING.COM> > Subject: Re: Factor Analysis: Number of Factors > To: SAS-L@LISTSERV.UGA.EDU > Date: Monday, July 6, 2009, 6:18 AM > "Mathur, Rajat" <Rajat.Mathur@DIAMONDCONSULTANTS.COM> > wrote > > > > >I have a very basic question in factor analysis - how > many factors to mention in nfactor option while running a > proc factor > > > > Basic, but far from simple or easy! True, very true!!! > &...

Re: Factor Analysis-How many factors I need
Peter L. Flom, PhD Assistant Director, Statistics and Data Analysis Core Center for Drug Use and HIV Research National Development and Research Institutes 71 W. 23rd St http://cduhr.ndri.org www.peterflom.com New York, NY 10010 (212) 845-4485 (voice) (917) 438-0894 (fax) >>> Irin later <irinfigvam@YAHOO.COM> 03/19/06 6:38 PM >>> wote <<< That is why I would like to FORCE program to generate 3 factors for my Baseline survey too instead 2 which output gave me. Actually specs are set at this time .I mean which question belong to which score (physical, emotio...

Re: Factor Analysis: Number of Factors #4
Dale McLerran <stringplayer_2@YAHOO.COM> wrote > >I would agree 100% with everything that Peter has written. I always like it when Dale agrees with me! >Instead of using visual examination of the scree plot or the >(liberal) eigenvalue>1 approach to determining the number of >factors to retain, I favor the approach known as "parallel >analysis". The method of parallel analysis has been around >since 1965. However, it has received little attention until >recently. The method of parallel analysis requires >resampling from the original data. Ei...

Re: Factor Analysis: Number of Factors #7
Something is seriously wrong with the Gmail editor It complete scrambles m= y text! I edited this version in Word: I make extensive use of both Factor Analysis & Principal Components Analyses. I mostly use both tools to reduce dimensionality in data sets of multidimensional reference axes (n-dimensional coordinate systems)--which are bipolar in nature. I deal with negative factor (or component) loadings by "reflecting" them so that all loadings are positive. In my work I deal with the mind, and I take an unapologetic approach that accepts the multidimensional nature of the ...

Re: Factor Analysis: Number of Factors #6
I make extensive use of both Factor Analysis & Principal Components Analyses. I mostly use both tools to reduce dimensionality in data sets of multidimensional reference axes (n-dimensional coordinate systems)--which are bipolar in nature. I deal with negative factor (or component) loadings by "reflecting" them so that all loadings are positive. In my work I deal with the mind, and I take an unapologetic approach that accepts the multidimensional nature of the mind phenomenon or mind event. If pushed, I will cite C. Lloyd Morgan's (following Alfred North Whitehead) notion...

Re: Factor Analysis: Number of Factors #5
Oops, I sent the almost unreadable unfinished version. Here is the corrected version I make extensive use of both Factor Analysis & Principal Components > Analyses. I mostly use both tools to reduce dimensionality in data sets = of > multidimensional reference axes (n-dimensional coordinate systems)--which > are bipolar in nature. I deal with negative factor (or component) loadin= gs > by "reflecting" them so that all loadings are positive. In my work I dea= l > with the mind, and I take an unapologetic approach that accepts the > multidimensional nature of...

Re: Factor Analysis: Number of Factors #2
"Mathur, Rajat" <Rajat.Mathur@DIAMONDCONSULTANTS.COM> wrote > >I have a very basic question in factor analysis - how many factors to mention in nfactor option while running a proc factor > Basic, but far from simple or easy! >I can select how many factors I want to analyze by checking the scree plot or by help of eigen value (>1), but if I run proc factor with nfactor=10 or nfactor=50 then loading on factors changes significantly and this even changes the business definition of my factors. > >Please help me understand how to choose the optimal value of ...

factor analysis
I am using factor analysis on various asset returns. Could not get factoran to work so I am using the function FA from FEX: function [B,L,var,fac,E] = FA(X,s) http://www.mathworks.com/matlabcentral/files/14115/FA.m where L is the rotated loading, var is the variability proportions and fac is estimated/rotated factors etc. Where I need help is how to convert 'fac' into observation space, the same as 'X' is in. What I want to do is to be able to plot 'fac' together with 'X' for comparison, or convert the returns back into asset values, which requires &...

Calculating factor scores for new dataset after factor analysis
Hello, I want to calculate the factor scores for a new "raw" dataset after I did a factor analysis with a "original" dataset, which is supposed to have the same structure as the new dataset. Unfortunately I got no idea how to do that yet and I'd be grateful if anybody could give me a hint. Bastian I haven't tried it with factor analysis, but with regression analysis the following worked. 1) Join the old file (file 1) and the new file (file 2). 2) Make a factor analysis, but use only the cases from file 1 (with the select subcommand) 3) The model w...

Factor Analysis
Is anyone aware of complications involved in running factor analysis on standardized Z-scores versus raw scores on variables. I wish to examine the factor structure of a summary score variable I created based on individual items pooled together from different sources. Thanks in advance Anthony Beckman URMC Anthony_Beckman@urmc.rochester.edu It's no problem for Exploratory factor analysis (EFA) since it operates on the correlation matrix anyway. As long as you don't round too much, the correlation matrices shouls be the same. For confirmatory factor analysis (CFA) the story is diff...

FACTOR ANALYSIS.
Respected Staticians/SAS users, I have used Factor analysis several times for cross sectional data. In one of my current assignments I have 'Time Series data' I was wandering if I could use Factor analysis for data reduction. If so what precautions need to be taken? if any. I would appreciate if any of you have any recommendations. (Basically the data has 12 months of data on 3 variables) Regards, Sajeel _________________________________________________________________ Getting married? Find great tips, tools and the latest trends at MSN Life Events. http://lifeevents.msn.com/categ...

factor analysis
Dear Group, I'm a novice at factor analysis and wanted to use SPSS for both exploratory and confirmatory factor analysis. A few questions about SPSS V.11 or 12 capabilities regarding factor analysis: 1. Re Confirmatory factor analysis: I understand that I can't use SPSS for confirmatory factor analysis - that I need to use AMOS. Has anyone used AMOS successfully for CFA? (I recall having trouble with it a number of years ago). If not, what user friendly software would you recommend? 2. Re Exploratory factor analysis: I am told that if there are different number of...

Regression factor scores from correlational matrix file factor analysis
Hello, Thank you in advance to anyone who can help me. I'm struggling to find infomation about this. Firstly, I am using SPSS. My data was not normally distributed so I created a correlational matrix file to do factor analysis. I then rotated my factor analysis (equamax rotation) and created factor scores using regression. This is my problem: I created factor scores but I don't know how to go about comparing men and women (the variable: sex) for each factor in my correlation matrix file because 'sex' is represented by a singular score. In the SPSS file, th...

Factor Analysis
read the SPSS output on a factor analysis? I conducted a factor analysis on 15 variables. The output mentions that 6 components were extracted. But which 6 components are those? Sincerely, Cortes On Mar 31, 8:51=A0pm, Cortes <nelson.cor...@gmail.com> wrote: > read the SPSS output on a factor analysis? > > I conducted a factor analysis on 15 variables. =A0The output mentions > that 6 components were extracted. =A0But which 6 components are those? > > Sincerely, > Cortes You should read up on factor analysis. Those components are underlying dime...

Minimun acceptable number of factors in factor analysis & tetrachoric correlation
Hi! Two naive questions... What would be the Minimun acceptable number of factors in factor analysis? Any reference to support this? What is tetrachoric correlation & how one could calculate this in SPSS? Thank you ! ...

Boolean Factor analysis
Hi all,=20 I am intrested in using factor analysis for data reduction purposes. Now = the issue I'm faced with is that=20 in my data set I have 4 continuious and 17 dummy variables.=20 My questions are. Should factor analysis be used for this at all? If yes, what precautions need to be taken? And is it recommend to to FA on just the dummy variables seperately? = Could any body direct me as to what code I should use for dummy factor = analysis.=20 Any help in the above matter will be appreciated.=20 Best regards, Sajeel Sajeel, I am not expert in factor analysis. However, it is ofte...

a question of factor analysis
Hi , when I tried the factor analysis ( fist time), there is a log message confused me: "The number of observations is not greater than the number of variables." Acturally there are 170 obs with 278 variables on the data. Would you give me some explainations and let me know if this going to have some bad effect? I'm trying to find the appropriate factors to fit model. Here is my code. proc factor data=data_1 method=principal scree mineigen=1 rotate=VARIMAX score NFACTORS=3 out=trash.factor1 outstat=trash.fact_all; run; Thank you very much. Understand that with 2...

factor analysis 379335
How are factor loadings calculated in factor analysis? any idea please? "Samoline1 Linke" <maganatewoman@yahoo.com> wrote in message <hem953$f88$1@fred.mathworks.com>... > How are factor loadings calculated in factor analysis? Look at: http://www.mathworks.com/access/helpdesk/help/toolbox/stats/factoran.html Branko ...