ApolloChoiceModelling forum

Dear Stephane,

Thank you very much for your thorough explanation. I believe this solves my problem, after accounting for the correlation between the h20 and h90 parameters, the LL improves compared with the basic model; this LL sits between the model using the same draw (perfect correlation) and that using two independent draws (no correlation), which makes sense theoretically. I feel I have learnt a lot here and thank you again.

Quick questions: in the correlated model you suggested, is preference dependence implied by the hinc_sig_20_90 parameter, e.g., a negative sign means that an individual who has a high sensitivity with 20% treatment would have a low sensitivity with 90% treatment? how do I calculate the correlation coefficient between the 20% and 90% parameters in Apollo? (especially calculating the standard error using Deltamethod?).

Thank you very much.

Tim

Tim

the sign of the correlation depends on the sign of the product of hinc_sig_20* hinc_sig_20_90. Section Section 9.2.5 in Kenneth Train's book. The Delta method can be used for this, but you'd need to work out the derivatives yourself - they're not implemented in Apollo for the standard errors.

Best wishes

Stephane

Hi Stephane,

Thanks a lot for your responses.

Tim