I wrote notes on demand estimation in industrial organization that survey a selected set of discrete choice techniques, from multinomial logit to Berry, Levinsohn, and Pakes (BLP)-type methods.

While originally intended as a study guide for a graduate industrial organization class, they can also serve as a high-level introduction for anyone who wants to use demand estimation.

The notes discuss conceptual and technical points, such as:

1. Differences between product space and characteristics space models
2. History and interpretation of the multinomial logit model
3. Bridging traditional demand estimation and industrial organization methods, by accounting for the correlation between unobserved quality and price
4. Understanding the random-coefficients logit demand model behind BLP, and the MPEC and nested fixed point versions of the BLP estimator
5. Extensions to standard BLP, including adding micro data (Micro BLP) and incorporating a supply side model
6. Econometrics of the BLP estimator
7. Remaining difficulties, and some applications (including merger simulation)

(Notes last updated August 2021.)