Forecasting new product penetration with flexible substitution patterns

We describe and apply choice models, including generalizations of logit called `mixed logits,ʹ that do not exhibit the restrictive `independence from irrelevant alternativesʹ property and can approximate any substitution pattern. The models are estimated on data from a stated-preference survey that elicited customersʹ preferences among gas, electric, methanol, and CNG vehicles with various attributes.