2

Is it possible to use exploratory factor analysis to extract four factors, and then combine these four factors (i.e. the factor scores for each observation) into a composite scale?

Patrick Coulombe
  • 2,536
  • 6
  • 20
  • 28
Lucy
  • 21
  • 2
  • 1
    Look into second order (or higher order) factor analysis. I think this is what you are looking for. – Jeremy Miles Feb 12 '14 at 23:44
  • This is another instance of this question: stats.stackexchange.com/questions/133492 I don't think you can meaningfully combine several factor/PC scores. – amoeba Jan 19 '17 at 16:44

1 Answers1

2

Yes, you can. Exploratory factor analysis aims to reducing data to a smaller set of summary variables... which are not the initial factors. But, depending on the EFA you used, you can use, for instance, a linear model based on the EFA score to reduce some factors in one. But, you should discrib a little bit more what analysis you think to use.

Leon-Alph
  • 80
  • 7
  • 1
    This is perhaps more of a comment than an actual answer. Perhaps you could develop your answer a little bit (e.g. detail what the "linear model" would be, give an example, etc.), or move your answer to the commentary section. – Patrick Coulombe Feb 12 '14 at 17:16
  • 1
    You're right, but I need 50 reputation to comment. – Leon-Alph Feb 12 '14 at 17:19
  • 1
    And I found this: http://stats.stackexchange.com/questions/22665/how-to-integrate-principal-components-with-glm – Leon-Alph Feb 12 '14 at 17:41