Multilevel ordered logistic models

Stata’s meologit allows you to fit multilevel mixed-effects ordered logistic models. A multilevel mixed-effects ordered logistic model is an example of a multilevel mixed-effects generalized linear model (GLM). You can fit the latter in Stata using meglm.

Here we replicate the three-level multilevel model example using the meologit command.

We have student-level data, where students are nested in classes, and classes are nested in schools. Our dependent variable thk is an ordered categorical variable that takes on the values 1, 2, 3, or 4; and we have three explanatory variables: prethk, cc, and tv. We will treat prethk as continuous. cc and tv are binary, and we want to include their interaction in the model. Let's fit an ordered logistic model:

. webuse tvsfpors

. meologit thk prethk cc##tv || school: || class:

Fitting fixed-effects model:

Iteration 0:  Log likelihood =  -2212.775
Iteration 1:  Log likelihood =  -2125.509
Iteration 2:  Log likelihood = -2125.1034
Iteration 3:  Log likelihood = -2125.1032

Refining starting values:

Grid node 0:  Log likelihood = -2152.1514

Fitting full model:

Iteration 0:  Log likelihood = -2152.1514  (not concave)
Iteration 1:  Log likelihood = -2125.9213  (not concave)
Iteration 2:  Log likelihood = -2120.1861
Iteration 3:  Log likelihood = -2115.6177
Iteration 4:  Log likelihood = -2114.5896
Iteration 5:  Log likelihood = -2114.5881
Iteration 6:  Log likelihood = -2114.5881

Mixed-effects ologit regression                 Number of obs     =      1,600

        Grouping information




               
 
                                            

 
     No. of       Observations per group

 Group variable
 
     groups    Minimum    Average    Maximum

 
 
         school
 
         28         18       57.1        137

          class
 
        135          1       11.9         28




Integration method: mvaghermite                 Integration pts.  =          7

                                                Wald chi2(4)      =     124.39
Log likelihood = -2114.5881                     Prob > chi2       =     0.0000


         thk 
 
 Coefficient  Std. err.      z    P>|z|     [95% conf. interval]
 
 
 
      prethk 
 
   .4085273    .039616    10.31   0.000     .3308814    .4861731
        1.cc 
 
   .8844369   .2099124     4.21   0.000     .4730161    1.295858
        1.tv 
 
    .236448   .2049065     1.15   0.249    -.1651614    .6380575
             
 
       cc#tv 
 
        1 1  
 
  -.3717699   .2958887    -1.26   0.209     -.951701    .2081612
 
 
 
       /cut1 
 
  -.0959459   .1688988                     -.4269815    .2350896
       /cut2 
 
   1.177478   .1704946                      .8433151    1.511642
       /cut3 
 
   2.383672   .1786736                      2.033478    2.733865
 
 
 
school       
 
   var(_cons)
 
   .0448735   .0425387                      .0069997    .2876749
 
 
 
school>class 
 
   var(_cons)
 
   .1482157   .0637521                       .063792    .3443674

LR test vs. ologit model: chi2(2) = 21.03                 Prob > chi2 = 0.0000

Note: LR test is conservative and provided only for reference.

Our model has two random-effects equations, separated by ||. Our first is a random intercept at the school level, and the second is a random intercept at the class level. The order we listed them matters: class comes after school, meaning that classes are nested within schools. Using the same logic, we could include more levels of nesting.

The output table includes the fixed-effect portion of our model, the estimated cutpoints (because this is an ordered logistic model), and the estimated variance components.

Also watch A tour of multilevel GLMs.