Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: mim prefix gllamm

From   William Trick <>
Subject   st: mim prefix gllamm
Date   Fri, 13 Apr 2012 13:25:38 -0500

I am trying to perform a mutilevel analysis using gllamm on an imputed dataset.

I received the already-imputed dataset from another investigator and
converted the dataset to Stata. I manipulated the dataset to include a
variable (m) that identifies the original dataset (m=0) and the five
imputed datasets (m=1-5). I also created two variables that identify
the imputed observations for the two imputed variables (i_var1,
i_var2). When I try to run the command, I receive the error "file
_mim_1.dta could not be opened".  I have been unable to open the data
to execute the command. Below is a sample of what I believe to be the
relevant code:

mi import flong, m(m) id(studyid) imputed(var1 var2)
mi describe
 Style:  flong

  Obs.:   complete        2,700
          incomplete          0  (M = 5 imputations)
          total           2,700
  Vars.:  imputed:  2; var1(0) var2(0)
          passive:  0
          regular:  0
          system:   3; _mi_m _mi_id _mi_miss

mi varying
       Possible problem   variable names
         unregistered varying:  (none)
  *unregistered super/varying:  (none)
   unregistered super varying:  m

mim, category(fit): gllamm var1 var3 var4 var5, i(clinic) link(logit)
family(binom) nip(12) adapt

mim, category(fit): gllamm var2 var3 var4 var5, i(clinic) link(logit)
family(binom) nip(12) adapt

Any suggestions would be appreciated.


William Trick
Collaborative Research Unit
1900 W. Polk St., Suite 1600
Chicago, IL          60612
Phone: (312) 864-3631

*   For searches and help try:

© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index