Parallel Inverse Aggregate Demand Curves in Discrete Choice Models

Working Paper: NBER ID: w27437

Authors: Kory Kroft; Ren Leal Vizcano; Matthew J. Notowidigdo; Ting Wang

Abstract: This paper highlights a previously-unnoticed property of commonly-used discrete choice models, which is that they feature parallel demand curves. Specifically, we show that in random utility models, inverse aggregate demand curves shift in parallel with respect to variety if and only if the random utility shocks follow the Gumbel distribution. Using results from Extreme Value Theory, we provide conditions for other distributions to generate parallel demands asymptotically, as the number of varieties increase. We establish these results in the benchmark case of symmetric products, illustrate them using numerical simulations and show that they hold in extended versions of the model with correlated tastes and asymmetric products. Lastly, we provide a “proof of concept” of parallel demands as an economic tool by showing how to use parallel demands to identify the change in consumer surplus from an exogenous change in product variety.

Keywords: Discrete Choice Models; Parallel Demand Curves; Consumer Surplus; Product Variety

JEL Codes: D01; D11; L0


Causal Claims Network Graph

Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.


Causal Claims

CauseEffect
exogenous change in the number of varieties in a market (D40)inverse aggregate demand curves shift vertically in parallel (E00)
number of varieties increases (C35)inverse aggregate demand curves are asymptotically parallel (E00)
parallel demands property (C69)identification of change in consumer surplus (D11)
sensitivity of demand to price while holding variety fixed and change in price and output in response to an exogenous change in variety (D11)identification of change in consumer surplus (D11)
identifying the vertical gap at one point on the demand curve (D11)ascertain the entire area between the two demand curves (R22)

Back to index