st: question about mi import ice

[Alex Lexus <alexlx208@gmail.com>]

Dear All,

I am trying to "mi import" a dataset (it is a panel dataset) that I
imputed using the ICE command in STATA 10, using the following syntax:

 mi import ice, automatic

I get the following error:

variables (_mj _mi) do not uniquely identify the observations
    at least one (_mj _mi) value is duplicated
r(459);

When I check for duplicates (where time is the time variable):

 duplicates report hhintid time _mj

Duplicates in terms of hhintid time _mj

--------------------------------------
   copies | observations       surplus
----------+---------------------------
        1 |       149870             0
--------------------------------------


 duplicates report hhintid time _mj _mi

Duplicates in terms of hhintid time _mj _mi

--------------------------------------
   copies | observations       surplus
----------+---------------------------
        1 |       149870             0
--------------------------------------

It seems that the mi import does not agree with the panel data
structure. Is this the case?
The imputations were run separately on each wave of the panel,
therefore there are repeated observations over time.

I then tried to import the data from 1 wave only. I get another error message:

 mi import ice, automatic
variable _mi has invalid values
    _mi takes on at least one value if _mj>1 that it does not if _mj==1

Would you have any suggestions on how to solve this?

Thanks in advance,

Alex

*
*   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/