We extend BLP's aggregate discrete-choice model of product differentiation to create more flexibility in the price functional form. We apply a Box-Cox specification, which relaxes the typical unit demand assumption and creates flexibility on demand curvature. The model provides a unifying framework for mixed logit and mixed CES models, while remaining computationally tractable. We provide an illustrative application to the ready-to-eat cereals market. This shows that the cross-sectional relation between price elasticities and average prices per product is more in line with descriptive elasticity patterns, and that substitution between product pairs may be affected to some extent.

We propose a methodology for estimating the competition effects from entry when firms sell differentiated products. We first derive precise conditions under which Bresnahan and Reiss’s entry threshold ratios (ETRs) can be used to measure competition effects. We then augment the traditional entry model with a revenue equation. This serves to adjust the ETRs by the extent of market expansion from entry, giving unbiased estimates of the competition effects. We apply our approach to seven local service sectors. We find that entry typically leads to significant market expansion, implying that traditional ETRs may substantially underestimate the competition effects from entry.

We propose a random coefficients nested logit (RCNL) model to compare the tractable nested logit (NL) model with the more complex random coefficients logit (RC) model. After a simulation study, we use data on the European automobile market. Both the NL and RC models are rejected against the RCNL model. The RC model results in different substitution patterns and a wider market definition than the NL and RCNL models. Nevertheless, the predicted price effects from mergers are robust across models. Our findings stress the importance of accounting for discrete sources of market segmentation not captured by continuous product characteristics.