Sanjoy posted on Thursday, June 02, 2005 - 8:33 pm
Dear Professor/s ... this is my model R by R1-R3; B by B1-B3; Y on R B X1; R on B X2; B on R X3; (X's share some common elements, Ri's and Bi's are 5 point ordered categorical and Y is 0/1)
I ran the model ...there is NO error message of any type, I checked twice, still I'm getting " ***** " under SE column, ... I asked for "TECH 3", from the ESTIMATED COVARIANCE MATRIX FOR PARAMETER ESTIMATES, I found for some parameters the value is exceptionally high and for some of them it's " *****"
Could you please tell me some possible remedies and why is it happening? ...thanks and regards
I have the following model with manifest categorical variables.
Model: w2_taet1 on w1_opf1 w1_taet1; w2_opf1 on w1_opf1 w1_taet1; w3_taet1 on w2_opf1w2_taet1; w3_opf1 on w2_opf1 w2_taet1;
w1_opf1 with w1_taet1; w2_opf1 with w2_taet1; w3_opf1 with w3_taet1;
If I have not the statement "categorical are" the estimation works well. With the statement, SE are not estimated for some variables. My question is, what is the fault in the categorical model and what statement is missed?
I have forgotten to write that the categorial variables are dichotomous. Could it be that the problem arises when I have a latent dependent variable which is predicted by dichotomous independent. The SE are not estimated than.
Thank you for your first answer and I am looking forward to hear from you.