I'd like to ask if I'm running a nonlinear mixed effect model for repeated measures of biomarker or echocardiographic measurements, how I can choose the nonlinear equation.
-
Login or Register
- Log in with
- You are not logged in. You can browse but not post. Login or Register by clicking 'Login or Register' at the top-right of this page. For more information on Statalist, see the FAQ.
-
-
You'd choose it based upon (i) the scientific question that you're trying to answer, (ii) the conditional distribution of the response (outcome) variable and (iii) what others who have worked in this area have successfully used in the past.Originally posted by Amr Ahmed View Post
Give precedence to the research question and the nature of the data over the mechanics—you might find that a generalized linear mixed model will adequately represent the phenomena, be easier to set up and be more likely to converge than a nonlinear mixed-effects regression model. Consider, for example, something along the following lines for a conventional repeated-measures (split-plot) study design.Code:meglm conc i.trt##i.tim || pid: , family(gaussian) link(log)
Comment