Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: micombine
Kristen Budd <firstname.lastname@example.org>
Re: st: micombine
Tue, 11 Jan 2011 11:36:52 -0500
If you are using ICE, the _mj represents your imputed data sets (ex.
logit var1 var2 if _mj==1, logit var1 var2 if _mj==2, etc.). Is "_mj"
your variable list in STATA? If not, you may need to reimpute your
original data. In the cases I have encountered, ICE/micombine will
still work with "non" micombine commands -- in this case you would get
a warning message in red that your command is not valid to use with
micombine. Even with this error, STATA "pushes" the analysis through
-- warning the results may not be valid.
Because you are getting an "_mj not found" error that leads me to
believe something is wrong with the imputed data set. Possibly check
your code and re-run ICE.
If the _mj is there, I'm afraid that's where my advice stops and
someone else will need to step in with additional advice.
On Tue, Jan 11, 2011 at 11:11 AM, Elisabetta Petracci
> Dear all,
> *I am using Stata 11 and referring to the paper published on Stata
> Journal "Multiple imputation of missing values" by Royston (2004).
> *Following the logic of the reported example, I need to impute missing
> values for dichothomous varaibles and then to run a quantile
> *regression on the complete datasets, considering m=5 copies of the
> *These are my 8 varaibles with missing values.
> mvis cometivedi1_new cometivedi2_new cometivedi3_new cometivedi4_new
> cometivedi5_new cometivedi6_new cometivedi7_new cometivedi8_new using
> trial, m(5) genmiss(m_) seed(1981)
> use trial,clear
> micombine qreg quantobuonasalute cometivedi1_new, quantile(.5)
> *"micombine" should work with command "qreg" but I get the following
> error message: "imputation identifier _mj not found"
> *Why does this happen? Any suggestion to impute missing values using a
> Multiple Imputation technique able to run a quantile *regression
> Thank you very much,
> * For searches and help try:
> * http://www.stata.com/help.cgi?search
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
Kristen M. Budd, MS
Department of Sociology
Stone Hall, Office 349A
700 W. State Street
West Lafayette, IN 47907
* For searches and help try: