I can't find any information on this at all using my usual source (google), I hope someone can answer me! My statistics teacher only wrote in her notes that this is "relevant in any dataset", but she didn't write (or say) anything about how
to solve the problem! Very useful... Thank you very much...
I'm going to do a survival analysis (Cox regression). I have dates for the following:
- start of follow-up
- event (disability pension)
- loss to follow-up (emigration)
- end of study (right censoring)
I need to combine these dates (or rather the days from start of follow-up to event or censoring) into one variable. But how do I do that? One subject can experience several of these events, but the event in question (disability pension) would be the first of them to occur, as you cannot get a disability pension if you are dead or have already retired. And if you emigrate, you won't end up in the disability pension registry.
I'm sure (or I hope) there is an easy way of doing this, but I simply can't find out what it is.
Can someone help me please?