Handling IIA violations with the Nested Logit model
If, however, your models violate the IIA, you need to resort to more advanced models. In this recipe, we will see one of them—a slightly more complicated Nested Logit model. The model groups similar alternatives into nests (hence the name). Given the limited space here, we will not discuss the intricacies of the model, but I highly recommend Kenneth Train's book that I referred to earlier in this chapter.
Getting ready
To execute this recipe, you need a working Python Biogeme package installed on your machine. No other prerequisites are required.
How to do it…
The skeleton of the model code remains the same; here, we will only show the changes (the Nested/dcm_nested.py file):
# add the coefficients to be estimated
C_price = Beta('C_price',0,-10,10,0,'C price' )
V_price = Beta('V_price',0,-10,10,0,'V price' )
Y_price = Beta('Y_price',0,-10,10,0,'Y price' )
Z_price = Beta('Z_price',0,-10,10,0,'Z price' )
ASC = Beta('ASC',0,-10,10,1,'ASC' )
B_refund...
