Cluster standard error for random effect logit model - without vce(bootstrap)?

[Yasemin Oez]

[COLOR=rgba(0, 0, 0, 0.87)]Hello everyone,
I have an issue with Stata and I would be grateful for your support. [/COLOR]

[COLOR=rgba(0, 0, 0, 0.87)]I'm working with an unbalanced penal data and use the "random effect logit model".
By that I mean, I'm using the following command:
xtlogit dep_var indep_var, re vce(bootstrap, rep(50) bca)

My issue is that with the vce(bootstrap) command, Stata needs forever to give me some output. Is there maybe another way to get clusteres standard errors for this -xtlogit, re command.


Thank you in advance.

Best regards,
Yasemin [/COLOR]

[Carlo Lazzaro]

Yasemin:
welcome to this forum.
Why not using -cluster- option instead of -bootstrap- (by the way, the -bca- option is computationally demanding)?

. use http://www.stata-press.com/data/r16/union.dta
(NLS Women 14-24 in 1968)

. xtlogit union age, re vce(cluster idcode)

Fitting comparison model:

Iteration 0:   log pseudolikelihood =  -13864.23 
Iteration 1:   log pseudolikelihood = -13851.221 
Iteration 2:   log pseudolikelihood = -13851.215 
Iteration 3:   log pseudolikelihood = -13851.215 

Fitting full model:

tau =  0.0     log pseudolikelihood = -13851.215
tau =  0.1     log pseudolikelihood = -13197.615
tau =  0.2     log pseudolikelihood =   -12662.4
tau =  0.3     log pseudolikelihood = -12222.052
tau =  0.4     log pseudolikelihood = -11854.374
tau =  0.5     log pseudolikelihood = -11544.892
tau =  0.6     log pseudolikelihood = -11287.102
tau =  0.7     log pseudolikelihood =  -11084.53
tau =  0.8     log pseudolikelihood = -10962.113

Iteration 0:   log pseudolikelihood = -11084.335 
Iteration 1:   log pseudolikelihood = -10669.142 
Iteration 2:   log pseudolikelihood = -10643.955 
Iteration 3:   log pseudolikelihood =  -10643.16 
Iteration 4:   log pseudolikelihood =  -10643.16  (backed up)
Iteration 5:   log pseudolikelihood = -10643.155 
Iteration 6:   log pseudolikelihood = -10643.155 

Calculating robust standard errors:

Random-effects logistic regression              Number of obs     =     26,200
Group variable: idcode                          Number of groups  =      4,434

Random effects u_i ~ Gaussian                   Obs per group:
                                                              min =          1
                                                              avg =        5.9
                                                              max =         12

Integration method: mvaghermite                 Integration pts.  =         12

                                                Wald chi2(1)      =      13.69
Log pseudolikelihood  = -10643.155              Prob > chi2       =     0.0002

                             (Std. Err. adjusted for 4,434 clusters in idcode)
------------------------------------------------------------------------------
             |               Robust
       union |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
         age |   .0192923    .005214     3.70   0.000      .009073    .0295115
       _cons |  -3.007968   .1691338   -17.78   0.000    -3.339464   -2.676472
-------------+----------------------------------------------------------------
    /lnsig2u |    1.81453   .0492249                      1.718051    1.911009
-------------+----------------------------------------------------------------
     sigma_u |   2.477538   .0609783                      2.360859    2.599983
         rho |   .6510557    .011183                      .6288307    .6726427
------------------------------------------------------------------------------

.