+ Reply to Thread
Results 1 to 3 of 3

Thread: Exploratory Factor Analysis with Ordinal Data

  1. #1
    Points: 881, Level: 15
    Level completed: 81%, Points required for next Level: 19

    Location
    Columbia, South Carolina
    Posts
    9
    Thanks
    3
    Thanked 0 Times in 0 Posts

    Exploratory Factor Analysis with Ordinal Data




    Hi folks,

    I am in the midst of absorbing as much information on exploratory factor analysis as I can. I studied this method once before but not to a great extent.

    My question is about using EFA with ordinal data. Consider this tutorial

    This tutorial performs EFA on six 7-point likert scaled manifest variables. The author does state that EFA on ordinal data is not ideal, however common in practice. Is this statement accurate? If so, what is the justification? If not, what methods are available for performing EFA with ordinal data?

    Thanks for you time

  2. #2
    Fortran must die
    Points: 58,790, Level: 100
    Level completed: 0%, Points required for next Level: 0
    noetsi's Avatar
    Posts
    6,532
    Thanks
    692
    Thanked 915 Times in 874 Posts

    Re: Exploratory Factor Analysis with Ordinal Data

    The statement is...in dispute.... You will get widely different opinions on this topic (I spent a lot of time reviewing this). The correlations that most EFA calculates is based on Pearson's and that is really not appropriate for ordinal data IMHO. You could try Spearman or polychoric correlations as an alternative. Most software won't generate polychoric correlations although there are work arounds for all major softwares (I know this is true for SAS, SPSS and R). For example SAS has a macro that does this.

    I don't think the issue is whether EFA can use likert data. I think it is the way EFA is performed commonly (with Pearson's correlations) that authors object to.
    "Very few theories have been abandoned because they were found to be invalid on the basis of empirical evidence...." Spanos, 1995

  3. #3
    Points: 881, Level: 15
    Level completed: 81%, Points required for next Level: 19

    Location
    Columbia, South Carolina
    Posts
    9
    Thanks
    3
    Thanked 0 Times in 0 Posts

    Re: Exploratory Factor Analysis with Ordinal Data


    Thanks for the reply

+ Reply to Thread

           




Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts






Advertise on Talk Stats