I previously posted a similar post in another thread. But I will try to clarify my question in the hope to get a reply. First I just want to say that I have little experience with statistics and that all help is welcome. I am writing my thesis in medicine.

I am using three surveys, let's call them A, B, and C. From one survey to the next, there is a 10-year interval. From these surveys, I calculate the weight change between A-B and B-C. I then check if they get a certain diagnosis after the calculated weight change within 10 years. I want to see if weight increase or decrease is associated with getting the disease.

I divided the data into two study samples:

Group AB: Those who participated in both A and B and did not have the diagnosis from before.

Group: BC: Those who participated in both B and C and did not have the diagnosis from before.

Some individuals participated in all three surveys and therefore are in both groups, so those will be counted in the dataset two times, although their observations of course are not the same. Maybe the person went up in weight between A and B and down in weight between B and C.

Then I have the individuals that are only in group AB and those that are only in group BC.

Initially, I performed a cox regression on the data, but then I understood that since some individuals are counted two times (in both groups), I have dependent data and therefore can not conduct such an analysis. From what I have understood I might need to perform some kind of multilevel analysis? Does someone here have any suggestions what analysis could be appropriate for my study?

Thanks a lot in advance.