Hello,

I just started working with Conquest (4.5.2). I ran a model with one dimension and a model with two dimensions.

Regarding the descriptive statistics, the frequencies of right and wrong answers (0,1) are slightly different than the frequencies in the data file. Often a difference of one case per item.

I am not sure if I did a mistake with the import or in the syntax.

Moreover, the twodimensional model breaks up. Error message: "Covariance matrix is not positive definite". Is this a problem of the syntax or is it that this model can not be estimated with this data.

I would be very grateful for your help.

Thank you,

Jonas