Can I use several different measures of the same variables and persons in a dataset for SEM analysis?

Hey guys,

I’m new here so I hope I on the right website here.
I am trying to prepare my data for analysis, and am not quite sure in which form I have to sort them.

I am doing a SEM analysis of dyads (APIMextendedMediation) by using an existing dataset. Now for every variable (x, y, m), I have several measures as the participants filled out questionnaires two times a day for 5 days.
So now I wanna see if same day x predicts same evening m which then predicts next-day y.
As I have several measures of each variable, I would like to use that data so that I have more power.
So I will have several seperate cases/case sets per person (Day 1 x, Day 1 m, Day 2 y; Day 2 x, Day 2 m, Day 3 y, Day 3 x, Day 3 m, Day 4 y, and so on…)

Like this, I will have 4 times more data than the actual sample.
My question now: Is this even “allowed”??? How do I have to state this in a paper, or what is this procedure even called?
And most importantly: how do I display this in my database? Will every separate “data set” be its own case/row, or do I do rows by person? I will use SPSS for the analysis, and I don’t really know how it will understand which variable is predicted by which one when I put everything in one single model together.

Hope my description makes at least some sense. I am very grateful about your answers!!

I can help with answering questions about IPUMS data and documentation, however these types of analytical questions are outside of the user support team’s purview (and in your case our expertise!). Perhaps someone else on the forum or in your department can help you with figuring out how to best run your analysis.