Login  Register

Re: Fwd: Latent Variable Analysis: CFA, EFA, and IRT?

Posted by David Marso on Jan 21, 2014; 8:54pm
URL: http://spssx-discussion.165.s1.nabble.com/Fwd-Latent-Variable-Analysis-CFA-EFA-and-IRT-tp5724030p5724050.html

"However, that requires either expensive extra software or using ad hoc software. "
Not necessarily true:
AFAIK there are a few FREE SEM solutions MX, LISREL has a free student version limited number of variables, there is an R package called lavaan (sp).  Probably others but I have not investigated.
OP take the time to do a little web search and you will likely locate them.

Art Kendall wrote
If you have a strong background, and good reasoning then CFA is
        the only way to be sure that your model fits.
        However, that requires either expensive extra software or using
        ad hoc software.
       
        Otherwise, if you have a good may many more cases than variables
        (10x?), a PAF with varimax rotation will give you a good shot at
        scales that have discriminative validity.  Be sure to keep only
        items that load cleanly if you retain more than 1 factor.
       
        It is possible that you will need to generate a larger items
        pool if you want to have items that measure more constructs.
       
        Parallel analysis will help you determine the number of factors
        to retain.
       
       
       
        Any thing more specific would depend on knowing the actual
        items, the eigenvalues, etc.
     
      Art Kendall
Social Research Consultants
      On 1/20/2014 4:46 PM, Deena Isom [via SPSSX Discussion] wrote:
   
   
     
       
        ---------- Forwarded message ----------
          From: Deena Isom < [hidden
              email] >
          Date: Mon, Jan 20, 2014 at 4:38 PM
          Subject: Latent Variable Analysis: CFA, EFA, and IRT?
          To: [hidden email]
         
         
         
            Hello List,
           
               
            I'm trying to determine which analytical strategy is
              best for a current project, and if any are adequately
              conducted in SPSS or if another stats package is needed.
             
            I'm trying to assess if two latent constructs are truly
              distinct, when in most literature items assessing
              each they are measured together in one scale..... I
              believe this is best done with exploratory factor
              analysis to see how different questions load of different
              factors, but if I believe they are different, would
              confirmatory factor analysis better serve these purposes -
              force their loadings?  Also, can either of these really be
              fully conducted in SPSS and provide information about fit
              and so forth?  And finally, could item response theory
              help distinguish which questions measure which concepts? 
              Honestly, I'm still confused by IRT. 
             
            Thanks in advance for your insight.  Hope you had a
              wonderful holiday!
           
               
                 
                  --
                  ~Deena
               
             
       
       
       
       
        --
        ~Deena
     
     
     
     
     
        If you reply to this email, your
          message will be added to the discussion below:
        http://spssx-discussion.1045642.n5.nabble.com/Fwd-Latent-Variable-Analysis-CFA-EFA-and-IRT-tp5724030.html 
     
     
        To start a new topic under SPSSX Discussion, email
        [hidden email] 
        To unsubscribe from SPSSX Discussion, click
          here .
        NAML
Please reply to the list and not to my personal email.
Those desiring my consulting or training services please feel free to email me.
---
"Nolite dare sanctum canibus neque mittatis margaritas vestras ante porcos ne forte conculcent eas pedibus suis."
Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff in abyssum?"