Skip to content

time*treatment vs time + time:treatment in RCTs

2 messages · Jorge Teixeira, Wolfgang Viechtbauer

#
Thank you, Philip.

1) would the model y (y1, y2 - but not y0) ~ y0 + time + time:treatment +
(1|ID) (*m3*) also violate the  principle of
marginality, in your opinion?

1.1) Would you still prefer m1 compared to m3?


*Final notes*:
Here is an interesting stata (sorry) about this:
https://stats.oarc.ucla.edu/stata/faq/what-happens-if-you-omit-the-main-effect-in-a-regression-model-with-an-interaction/


Solomon's post.
https://solomonkurz.netlify.app/post/2022-06-13-just-use-multilevel-models-for-your-pre-post-rct-data/

Thanks!




Phillip Alday <me at phillipalday.com> escreveu no dia segunda, 29/08/2022
?(s) 14:26:

  
  
#
If 'time' is categorical, then neither m2 nor m3 violate the 'principle of marginality'.

Best,
Wolfgang