Estimating Separable Matching Models

TL;DR

This paper introduces two straightforward estimation methods for separable matching models with transferable utility, utilizing generalized entropy and GLMs, enhancing the toolkit for analyzing matching markets.

Contribution

It presents novel estimation techniques for separable matching models, expanding practical tools for empirical analysis in matching markets.

Findings

Two estimation methods are proposed: a minimum distance approach and a GLM-based approach.

Both methods are designed to be simple and computationally feasible.

The methods are applicable to models with transferable and separable utility.

Abstract

In this paper we propose two simple methods to estimate models of matching with transferable and separable utility introduced in Galichon and Salani\'e (2022). The first method is a minimum distance estimator that relies on the generalized entropy of matching. The second relies on a reformulation of the more special but popular Choo and Siow (2006) model; it uses generalized linear models (GLMs) with two-way fixed effects.