4

I’ve had a student complete a piece of work with some great data. I am considering re-analysing the data for publication. SEM makes sense, but the model is both formative and reflective. How can I overcome this issue?

Nick Cox
  • 48,377
  • 8
  • 110
  • 156
user205985
  • 41
  • 1
  • 1
    What do you mean by "formative" and "reflective"? – Giuseppe Biondi-Zoccai Apr 26 '18 at 08:20
  • 1
    Thanks for your comment. Really good explanation found here: https://stats.stackexchange.com/questions/184947/what-is-the-difference-between-formative-and-reflective-measurement-models – user205985 Apr 26 '18 at 16:17
  • 1
    One example of a model with both kinds of indicator is a MIMIC model, see, for example: https://stats.stackexchange.com/questions/189462/whats-the-difference-between-a-mimic-factor-and-a-composite-with-indicators-se But there's nothing special that you need to do - just put them both in. – Jeremy Miles Apr 26 '18 at 17:06
  • Please clarify what "the issue" is here. – Gregg H Apr 27 '18 at 20:17
  • Thanks Jeremy Miles, this is exactly what I was looking for :-D :-D – user205985 Apr 28 '18 at 21:45

0 Answers0