Testing for significant within group change for longitudinal data

Melk — Thu, 02 Nov 2017 00:11:19 GMT

I am using a mixed model and restricting the analysis to a single group of interest using a where statement in my model. There are 3 visits. I would like to know if there is a significant change in my outcome variable over time. If I treat my visits as continuous, will the fixed effect p-value for visit tell me if my outcome significantly changed over time? Not sure how to treat visit here.

Re: Testing for significant within group change for longitudinal data

sld — Thu, 02 Nov 2017 02:28:17 GMT

I would benefit from more detail (like code and example data). I'm not sure how the "where" restriction fits in. If it's a mixed model, then you might want to consider random coefficients. Until more detail is available...

If you incorporate visits as continuous then (by default and depending on details), you are fitting a linear regression of the outcome on visit. This would be a somewhat crude assessment of trend that assumes linearity. Of course, with only 3 visits, it could be hard to assess the validity of the linearity assumption, and a "crude" assessment might just fine. I've taken this approach before and been comfortable with it.

You might find the SAS Statistical Procedures to be a better forum for this question. I have the (recently acquired) power to move your post, but I've never done that before. Let me know if you'd like me to (try to) move it 🙂

topic Testing for significant within group change for longitudinal data in Statistical Procedures

Testing for significant within group change for longitudinal data

Re: Testing for significant within group change for longitudinal data