I ran 4 separate two-parameter logistic IRT models. Two of them worked fine. The other two ran, but for two of my variables (one in each of the models) mPlus reads that there are three categories. In both instances, once case is in the "phantom" third category. I say "phantom" because I ran frequencies on the data prior to reading them into mPlus and these two variable (like all the other in both models) are dichotomous. I even played around with the formatting of data file, and meticulously eyeballed the variables in the .dat file -- all 131 cases. Can anyone reckon why this is happening?
You either have blanks in the data set which are not allowed with free format data or you have more names in the NAMES list than columns in your data set causing the date to be misread. If you can't see the issue, please send the output, data set, and your license number to firstname.lastname@example.org.