Timeline for Linear mixed effects model on physiological parameter as function of time
Current License: CC BY-SA 3.0
4 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Aug 4, 2017 at 19:00 | comment | added | EdM | @Lucas the specifications of mixed models like yours may include implicit assumptions about correlations between intercepts and slopes. See here and here for examples. As for your model being "correct," that depends on what you are trying to accomplish and how well your model represents the data. To me, intercepts alone would seem most related to being "consistently the highest over time." You will have to evaluate carefully how well your model fits your data, as for any regression. | |
| Aug 4, 2017 at 18:32 | comment | added | Lucas | I cannot give you the green check since I have less than 15 points (I registered here a couple of days ago) | |
| Aug 4, 2017 at 18:30 | comment | added | Lucas | Thanks so much for your reply, @EdM. Most of the slopes for individual subjects are positive regarding HDL against Age, but a substantial number is negative, and the slopes vary a lot. I will then specify the slope as (Age | ID). I have removed subjects with <3 observations to avoid the problem of number of measurements = 1. Assuming HDL increases linearly with Age, would you say the following model is now correct?. model2 = lmer(HDL ~ Age + Sex + Tanner + (Age|ID), data). Thanks ! | |
| Aug 4, 2017 at 17:31 | history | answered | EdM | CC BY-SA 3.0 |