Announcement

Collapse
No announcement yet.
X
  • Filter
  • Time
  • Show
Clear All
new posts

  • Checking Linearity Assumption in Multivariate Mixed Model

    Hi, I'm not sure the best way to check the linearity assumption of a multivariate mixed model. The model is looking at blood oleic acid levels for individuals that were measures 3 times. The model I ran is as follows:

    So i know using multivariate linear regression Stata allows you to run a component-plus-residuals plot (partial residuals plot), is there any way to do this from a mixed model or any more appropriate test?

    Thank you!
    Attached Files

  • #2
    Many of these tools are readily available for regression but not for other models. I suspect you can easily program and run a Ramsey reset test. If you look on this listserv you will find it explained in detail.

    Comment


    • #3
      Is age your time variable? If so, then for starters you can (optionally) mean-center it, create polynomial terms of that and inspect their regression coefficients. You can do the same with the body-weight variable, too, if you're concerned about it.

      Comment

      Working...
      X