Latent variable model analysis is an analytical method that defines some property behind the object of analysis that cannot be directly observed as a latent variable and assumes that the latent variable is indirectly observed. Latent variable models are classified into four types according to the combination of the scale of the observed variable and the latent variable. When the observed variable is continuous and the latent variable is also continuous, it is factor analysis. When the observed variable is continuous and the latent variable is also discrete, it is finite mixture model. When the observed variable is discrete and the latent variable is continuous, it is item response theory model. When the observed variable is discrete and the latent variable is also discrete, it is latent class analysis. Of these four analytical methods, latent class analysis is not implemented in SAS and can only be performed in JMP Pro. In this presentation, we will introduce latent variable model analysis using JMP while explaining the relationship between these four analytical methods.
