This paper speci…es and estimates a structural dynamic model of consumer demand for new and used durable goods. Its primary contribution is to provide an explicit estimation procedure for transaction costs, which are crucial to capturing the dynamic nature of consumer decisions. In particular, transaction costs play a key role in determining consumer replacement behavior in both primary and secondary markets for durable goods. The unique data set used in this paper has been collected by the Italian Motor Registry and covers the period from 1994 to 2004. It includes information about sales dates for individual cars over time as well as the initial stock of cars in the sample period. Identi…cation of transaction costs is achieved from the variation in the share of consumers choosing to hold a given car type each period, and from the share of consumers choosing to purchase the same car type that period. Speci…cally, I estimate a random coe¢ cients discrete choice model that incorporates a dynamic optimal stopping problem in the spirit of Rust (1987). I apply this model to evaluate the impact of scrappage subsidies on the Italian automobile market in 1997 and 1998. This paper has bene…ted greatly from discussions with Marc Rysman. Special thanks are also due to Victor Aguirregabiria, Michael Manove, Martin Pesendorfer and seminar participants at several institutions.

In many competitive settings consumers buy multiple product categories, and some prefer to use a single firm, generating complementary cross-category price effects. To study pricing in supermarkets, an organizational form where these effects are internalized, we develop a multi-category multi-seller demand model and estimate it using UK consumer data. This class of model is used widely in theoretical analysis of retail pricing. We quantify crosscategory pricing effects and find that internalizing them substantially reduces market power.We find that consumers inclined to one-stop (rather than multi-stop) shopping have a greater pro-competitive impact because they generate relatively large cross-category effects.

This paper speci…es and estimates a structural dynamic model of consumer demand for new and used durable goods. Its primary contribution is to provide an explicit estimation procedure for transaction costs, which are crucial to capturing the dynamic nature of consumer decisions. In particular, transaction costs play a key role in determining consumer replacement behavior in both primary and secondary markets for durable goods. The unique data set used in this paper has been collected by the Italian Motor Registry and covers the period from 1994 to 2004. It includes information about sales dates for individual cars over time as well as the initial stock of cars in the sample period. Identi…cation of transaction costs is achieved from the variation in the share of consumers choosing to hold a given car type each period, and from the share of consumers choosing to purchase the same car type that period. Speci…cally, I estimate a random coe¢ cients discrete choice model that incorporates a dynamic optimal stopping problem in the spirit of Rust (1987). I apply this model to evaluate the impact of scrappage subsidies on the Italian automobile market in 1997 and 1998. This paper has bene…ted greatly from discussions with Marc Rysman. Special thanks are also due to Victor Aguirregabiria, Michael Manove, Martin Pesendorfer and seminar participants at several institutions.

The paper analyzes a durable goods monopoly problem in which multiple varieties can be sold. A robust Coase conjecture establishes that the market eventually clears, with profits exceeding static optimal market-clearing profits and converging to this lower bound in all stationary equilibria with instantaneous price revisions. Pricing need not be efficient, nor is it minimal (equal to the maximum of marginal cost and minimal value), and can lead to cross-subsidization. Conclusions nest both classical Coasian insights and modern Coasian failures. The option to scrap products does not affect results qualitatively, but delivers a novel motive for selling high cost products. (JEL C78, D42, L12)

We show FC-MNL is flexible in the sense of Diewert (1974), thus its parameters can be chosen to match a well-defined class of possible ownand cross-price elasticities of demand. In contrast to models such as Probit and Random Coefficient-MNL models, FC-MNL does not require estimation via simulation; it is fully analytic. Under well-defined and testable parameter restrictions, FC-MNL is shown to be an unexplored member of McFadden's class of Multivariate Extreme Value discretechoice models. Therefore, FC-MNL is fully consistent with an underlying structural model of heterogeneous, utility-maximizing consumers. We provide a Monte-Carlo study to establish its properties and we illustrate the use by estimating the demand for new automobiles in Italy.