Marketing researchers have used models of consumer demand to forecast future sales; to describe and test theories of behavior; and to measure the response to marketing interventions. The basic framework typically starts from microfoundations of expected utility theory to obtain an econo-metric system that describes consumers ' choices over available options, and to thus characterize product demand. The basic framework has been augmented significantly to account for quantity choices; to accommodate purchases of several products on a single purchase occasion (multiple discreteness and multi-category purchases); and to allow for asymmetric switching between brands across different price tiers. These extensions have enabled researchers to bring the analysis to bear on several related marketing phenomena of interest. This paper has three main objectives. The first objective is to articulate the main goals of demand analysis forecasting, measurement and testing and to highlight several considerations associated with these goals. Our second objective is describe the main building blocks of individual-level demand models. We discuss approaches built on direct and indirect utility specifications of demand systems, and review extensions that have appeared in the Marketing literature. The third objective is to explore a few emerging directions in demand analysis including considering demand-side dynamics; combining purchase data with pri-mary information; and using semiparametric and nonparametric approaches. We hope researchers new to this literature will take away a broader perspective on these models and see potential for new directions in future research.

(Article begins on next page) The Harvard community has made this article openly available. Please share how this access benefits you. Your story matters.

Abstract Digitization of content is changing how consumers and firms use purchase and rental markets. Low transaction costs make accessing content easier for consumers. Digital technology enables firms to create non-durable "rental" versions of their content and restrict content to the purchasing consumer, effectively shutting down resale markets. To empirically analyze the interaction of purchase and rental markets, I design a preference measurement tool to recover consumers' inter-temporal preferences through currentperiod choices alone. I then use these preferences to solve for a dynamic equilibrium between consumers and the firm. In the context of the online home-video market, I find that when the firm is able to commit to holding prices fixed forever, providing content through the purchase market alone is sufficient. However, when the firm is unable to commit, it should serve both purchase and rental markets. Canonical theory models would predict exclusive rentals, but the purchase option enables indirect price discrimination in practice. I also find that when consumers place a premium on accessing new content, they are less likely to inter-temporally substitute, thereby increasing the firm's pricing power. Consistent with theory, commitment to future prices increases profits considerably. This finding supports the rigid pricing structure of such retailers as Apple, despite studios' push toward more pricing flexibility. Keywords: purchase and rental markets, durable good pricing, online content, experiment design, conjoint analysis * This paper is based on my dissertation. I would like to thank my advisor Wesley Hartmann for his invaluable guidance. I would also like to thank my dissertation committee members Harikesh Nair, Sridhar Narayanan and V. Srinivasan for their valuable feedback. Thanks to Latika Chaudhury, Pradeep Chintagunta, J.P.Dubé, Avi Goldfarb, Günter Hitsch, Oleg Urminsky; to seminar participants at Chicago, Cornell, Dartmouth, Northwestern, Ohio State, Rochester and UBC; to participants at the

An existing theoretical literature finds that frictionless resale markets cannot reduce profits of monopolist producers of perfectly durable goods. This paper starts by presenting logical arguments suggesting this finding does not hold for goods consumers tire of with use, implying the impact of resale is an empirical question. The empirical impact is then estimated in the market for video games, one of many markets in which producers may soon legally prevent resale by distributing their products digitally as downloads or streamed rentals. Estimation proceeds in two steps. First, demand parameters are estimated using a dynamic discrete choice model in a market with allowed resale, using data on new sales and used tradeins. Then, using these parameter estimates, prices, profits, and consumer welfare are simulated under counterfactual environments. When resale is allowed, firms are unable to prevent their goods from selling for low prices in later periods. The ability to do so by restricting resale outright yields significant profit increases. Renting, however, does not raise profits as much due to a revenue extraction problem. (JEL M30, L00, K19) 1

This paper studies the impact of pricing choices by platform intermediaries in a two-sided market with positive indirect network e ects. It presents a dynamic equilibrium model to analyze consumers ' purchase decisions for competing hardware platforms and a liated software products, and software rms ' dynamic pricing and entry decisions. This paper develops a new Bayesian approach for structural estimation of dynamic games. The estimation method is implemented on the U.S. fth-generation video game industry (May 1995- February 2002). The results show that overpricing one side of the market not only discourages demand on that side but also discourages participation on the other side, which over time can lead to a death spiral.

We develop a new empirical strategy for identifying the parameters of dynamic structural models in markets for storable goods, with a focus on identification of the discount factor. The identification strategy rests on an exclusion restriction generated by discontinuities in package sizes: In storable goods product categories where consumption rates are exogenous and package sizes are discrete, current utility does not depend on inventory unless a package gets used up. Most of the time, inventory only enters a consumer’s expected future value. We develop conditions for identification in two situations: when inventory is observed to the researcher, and when it is unobserved. When inventory is unobserved, we show that the shape and slope of the purchase hazard can identify the discount factor. We demonstrate the feasibility of our identification strategy with an empirical exercise, where we estimate a stockpiling model using scanner data on laundry detergents. Preliminary estimates suggest that consumers are not as forward-looking as most papers in the literature assumes; our estimates of weekly discount factors average at about 0.91, which is significantly lower than the value used in previous research (it typically is set at 0.99, using the market interest rate). We also find evidence of significant unobserved heterogeneity in discount factors, estimating the 25th and 75th percentiles of the population distribution of discount factors to be 0.88 and 0.96.

Copyright by