Estimation of discrete choice models including socio-economic explanatory variables

Discrete choice models and qualitative response models are intimately related. Usually both are based on a logistic specification. In many applications the two approaches have been combined leading to a 'discrete choice model including socio-economic explanatory variables'. The paper desdribes maximum likelihood estimation for all three approaches. Special attention is given to the case of missing variation (over individuals) of category-dependent explanatory variables.