I am conducting a survey to analyze the effect of a binary variable X on a latent variable Y. The effect is assumed to be mediated by another latent variable M. Moreover, the effect of X on M is assumed to be moderated by a latent variable W.
My research on how to statistically examine this relationship led me to two different approaches:
- Conditional Process Analysis with the SPSS macro PROCESS
- A Structural Equation Model
Which one should I prefer and for what reasons?
I have read the following paper comparing the two approaches, but am still not able to make a decision: https://www.sciencedirect.com/science/article/abs/pii/S1441358217300265
Thank you very much for your help!