value added model through a multilevel or mixed (mixed)

[Oscar Cerquera]

Hello,
I need help with a problem.
I am estimating a university value added model through a multilevel or mixed (mixed command in stata), with two levels (student level and university level); the model estimates me the residuals and/or variances of level 1 (var(Residual)) and level 2 ( var(_cons)). I need to predict the level 2 variance, because it is the one that calculates the aggregate value, but I don't know which command to use (predict resid, residual estimates the level 1 residuals).

[Clyde Schechter]

predict wanted, reffects relevel(university)

Replace university by the name of the variable you used to define the university level in your -mixed- command.

[Oscar Cerquera]

Hi Clyde, thank you very much, it ran very well.
Just one question, and it has to do with interpretation. The negative values mean that the university did not generate added value and on the contrary the students performed better at school than at university.
Or this prediction does not serve to calculate that value but to rank or order the universities from highest to lowest value added.
Thanks again.

[Clyde Schechter]

A negative value of the university-level residual means that after adjusting for all other model variables and for the residuals at other levels, the average observed outcome for that university's observations was below the average for all universities.

[Oscar Cerquera]

Thank you very much