SPSS help

[ranjana Soni]

Dear All,

I am trying to run a MNL model on my data. However I am getting the results with the following error stated in the beginning . Please guide if this needs to be ignored and if not , how to rectify this. The SS is 287.

Thanks in advance,
Ranjana




Warnings

There are 297 (65.3%) cells (i.e., dependent variable levels by subpopulations) with zero frequencies.

Unexpected singularities in the Hessian matrix are encountered. This indicates that either some predictor variables should be excluded or some categories should be merged.

The NOMREG procedure continues despite the above warning(s). Subsequent results shown are based on the last iteration. Validity of the model fit is uncertain.

[Rich Ulrich]

On Fri, 14 Aug 2020 10:55:50 -0700 (PDT), ranjana Soni

Post by ranjana Soni
Dear All,
I am trying to run a MNL model on my data. However I am getting the results with the following error stated in the beginning . Please guide if this needs to be ignored and if not , how to rectify this. The SS is 287.
Thanks in advance,
Ranjana
Warnings
There are 297 (65.3%) cells (i.e., dependent variable levels by subpopulations) with zero frequencies.
Unexpected singularities in the Hessian matrix are encountered. This indicates that either some predictor variables should be excluded or some categories should be merged.

"This indicates that either some predictor variables should
be excluded or some categories should be merged."

Do it. One or the other or both.

If you need to ask a followup, we can say more if we know...

What is your N? What is your number of predictors?
What is the total d.f. of the predictors?
What is your model?

Post by ranjana Soni
The NOMREG procedure continues despite the above warning(s). Subsequent results shown are based on the last iteration. Validity of the model fit is uncertain.

Assume "no validity" until you understand what is going on,
and understand why it does not matter (if that does happen
to be the case).