We present a new methodology to estimate dynamic discrete choice models with aggregate data; the estimation allows for a multi-dimensional state space, but still retains signicant computational benets. We specically build upon the literature pertaining to the dynamic single-agent models with conditional choice probabilities by including both observed and unobserved population state variables in estimation. We demonstrate that the approach performs well in accurately recovering the estimated parameters via Monte Carlo simulations, and that it compares favorably with the current state-ofthe-art methods. We illustrate with an empirical application to assess the impact of dynamics in the digital camera market.

We analyze mixed bundling in two-sided markets where installed base effects are present and find that the pricing structure deviates from traditional bundling as well as the standard two-sided markets literature—we determine prices on both sides fall with bundling. Mixed bundling acts as a price discrimination tool segmenting the market more efficiently. Consequently, as a by-product of this price discrimination, the two sides are better coordinated, and social welfare is enhanced. We show unambiguously that platform participations increase on both sides of the market. After theoretically evaluating the impact mixed bundling has on prices and welfare, we take the model predictions to data from the portable video game console market. We find empirical support for all theoretical predictions. This paper was accepted by J. Miguel Villas-Boas, marketing.

Several key questions in bundling have not been empirically examined: Is mixed bundling more effective than pure bundling or pure components? Does correlation in consumer valuations make bundling more or less effective? Does bundling serve as a complement or substitute to network effects? To address these questions, we develop a consumer-choice model from micro-foundations to capture the essentials of our setting, the handheld video game market. We provide a framework to understand the dynamic, long-term impacts of bundling on demand. The primary explanation for the profitability of bundling relies on homogenization of consumer valuations for the bundle, allowing the firm to extract more surplus. We find bundling can be effective through a novel and previously unexamined mechanism of dynamic consumer segmentation, which operates independent of the homogenization effect, and can in fact be stronger when the homogenization effect is weaker. We also find that bundles are treated as separate products (distinct from component products) by consumers. Sales of both hardware and software components decrease in the absence of bundling, and consumers who had previously purchased bundles might delay purchases, resulting in lower revenues. We also find that mixed bundling dominates pure bundling and pure components in terms of both hardware and software revenues. Investigating the link between bundling and indirect network effects, we find that they act as substitute strategies, with a lower relative effectiveness for bundling when network effects are stronger.

No abstract

No abstract