st: RE: assertion is false error: mvencode

[Red Owl <rh.redowl@liu.edu>]

Linda (and other who may be interested),

I believe this error occurs when you try to run the LCA Stata Plugin from The Methodology Center at Penn State (http://methodology.psu.edu/downloads/lcastata) on binary variables that are coded as 0/1.  The data must be positive integers, so you might try to add 1 to any binary variables coded as 0/1 and then attempt to rerun your analysis.

Also, if you are using Stata/IC (not recommended by the plugin authors but possible with some data and problems), you need to include the option maxiter(800) in the LCA code.  That is necessary due to the maximum matrix size limitations of Stata/IC.  If you are using a higher version of Stata, you should set maxiter(5000) or higher.

Red Owl


>> O'Keeffe, Linda" <L.OKeeffe@ucc.ie<mailto:L.OKeeffe%40ucc.ie>>
>>
>> I am using Penn State University doLCA command. I keep getting an error after some of the code has run saying
>>
>> "389 contradictions in 708 observations"
>>
>> assertion if false
>>
>> r (9)
>>
>> r (9) error code says "   error . . . . . . . . . . . . . . . . . . . . . . . . .  Return code 9
>>
>>         assertion is false;
>>
>>         no action taken;
>>
>>         Return code and message from assert when the assertion is false;
>>
>>         see [D] assert.
>>
>>         Or, you were using mvencode and requested Stata change `.' to #
>>
>>         in the specified varlist, but # already existed in the varlist,
>>
>>         so Stata refused; see [D] mvencode.
>>
>> (end of search)
>>
>> I assume this is a problem with my data but I don't know what. Any assistance would be most greatly appreciated!
>> Linda

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/