Dr Alessandro Iaria, University of Bristol

"Identification and Estimation of Demand Models with Endogenous Product Entry"
Friday, 10 March. 3:00 pm
Room 305. Main Building

Abstract

The estimation of demand models for differentiated products often relies on data from multiple geographic markets and time periods. The fact that firms do not offer some products in some markets generates a problem of endogenous selection in demand estimation. The non-additivity of demand unobservables in firms' expected profit and the potential multiplicity of equilibria in the entry game, make this selection problem challenging. Standard two-step methods to account for selection provide inconsistent estimates of structural parameters. Recent proposed methods require parametric assumptions on the distribution of unobservables as well as repeatedly computing the equilibria of the game. In this paper, we show the identification of demand parameters in a structural model of demand, price competition, and market entry that allows for a nonparametric distribution of demand unobservables. We propose a two-step method that extends standard techniques to control for selection bias. We illustrate our method using simulated data and real data from the airline industry. We show that not accounting for endogenous product entry generates substantial biases that can be even larger than those from ignoring price endogeneity.

"Identification and Estimation of Demand Models with Endogenous Product Entry" by Alessandro Iaria (University of Bristol), Victor Aguirregabiria (University of Toronto) and Senay Sokullu (University of Bristol)

Bio

Alessandro Iaria is a senior lecturer in economics at the University of Bristol, a research associate at the IFS, and a research affiliate at the CEPR. He does research on two main topics: the economics of science and innovation, and the econometrics of structural models used in industrial economics. On a first series of projects, Alessandro has been studying the path-breaking developments of the natural sciences in the 20th century and their impact on technological progress. On a different line of research, he has been investigating several issues that commonly arise in the estimation of discrete choice models of demand and representing games of strategic interactions.


For further information, don't hesitate to get in touch with business-school-research@glasgow.ac.uk.

We foster a positive and productive environment for seminars through our Code of conduct.

First published: 28 February 2023

<< 2023