Adding in levels to STATA

[Abby Stewart]

Hi, I am an undergraduate student attempting repeat measure multilevel modelling for my dissertation and would really appreciate help in producing the code for my project!

I am studying protein intake of high school students and seeing whether breakfast, lunch or dinner provides the most protein. I'm planning on doing this through regression using the overall daily protein intake.

I have collected their intake over two 24 hour periods (therefore have repeated measures data.)
My levels are level 2 (day of observation (either first or second 24hr period)), level 3 ( Pupil ID) and level 4 (School ID).

I am normally used to working with data that has only one level such as school, and would start off by doing
" TotalProtein || SchID: " to assess the LR test, followed by " estat ICC " to further assess.

However when working with multiple levels such as school, pupil, day of observation... Do I enter all levels initially like..
" TotalProtein || SchID : || PupilID: || DayObs "
Or add one by one, or test individually?

Thank you so much for your advice!
Best wishes,
Abby

[Marcos Almeida]

You may start with a simpler model, such as the one with the levels. Then, you add the variables in the left part of the command (fixed effects). After that, you may play with interaction terms as well as the addition of random slopes for some variables, having checked the eventual improvement of the model with postestimations. Please type - help mixed - to have a view of the possibilities.