

Proportion of Variance in Latent Inte... 

Message/Author 

Joseph posted on Thursday, February 06, 2014  6:19 pm



Hello Dr.Muthen, For a simple latent interaction model, A BY A1 A2; P BY P1 P2; AxP  A XWITH P; Y ON A P AxP; I am able to calculate the proportion of variance contributed by the interaction term (AxP) by the formula (19) mentioned at : https://www.statmodel.com/download/LV%20Interaction.pdf However , I am wondering how I can calculate the proportion of variance contributed by 'A' Can I calculate it as (squared unstandardized loading of A * Variance of A )/ Variance of Y. And if the variance of A is set as 1 : A@1; Then : proportion of variance contributed by 'A' = Squared unstandardized loading of A / Variance of Y Am I correct in my understanding 


A is correlated with P so the variance decomposition isn't clear. I wouldn't use that proportion. 

Back to top 

