Consumer heterogeneity, demand for durable goods and the dynamics of quality

This paper develops a methodology to estimate models of demand for differentiated durable goods with fully heterogeneous consumers. It expands standard discrete choice models by endogenizing purchase timing decisions using a participation function which is the result of the consumers’ dynamic optimization problem. A “nested†technique is used to uncover a reduced form of this function, which depends on the preferences and on the intertemporal distribution of the quality and prices of available products. The presence of such reduced form serves as the control for the dynamic optimization problem and al- lows a consistent estimation of the deep preference parameters, which can in turn be used to compute the complete dynamic problem. A simple application to the market for digital cameras is used to demon- strate the feasibility of the technique. The methodological framework has potential applicability in other dynamic demand problems. It is also substantially less costly than alternative estimation approaches, which in principle require the computation of the dynamic optimiza- tion problem across all consumer types and through all the steps of the estimation algorithm