Econometrics, Quantitative Economics, Data Science

TraME

TraME (test version)

R implementation of the “TraME” library

Description

TraME (Transportation Methods for Econometrics) is a toolbox for solving problems of equilibrium computation and estimation in discrete choice and matching problems using Optimal Transport techniques.

Presentation slides are available here.

TraME core team: Alfred Galichon, Keith O’hara, Simon Weber.

Sources

Available from GitHub here.

Installation and testing

First, install Gurobi along with the proper R interface package. Then, the quickest way to install TraME is via the devtools package.

install.packages("devtools")
library(devtools)
install_github("TraME-Project/TraME-Classic")

The TraME test routines are invoked as follows:

library(TraME)
library(gurobi)
tests_TraME()

Documentation coming soon.

Bibliography

O. Bonnet, A. Galichon, and M. Shum (2015): “Yoghurt Chooses Man: The Matching Approach to Identification of Nonadditive Random Utility Models”.
K. Chiong, A. Galichon, and M. Shum (2014): “Duality in Dynamic Discrete Choice Problems”.
A. Galichon, Y.-W. Hsieh (2015): “Love and Chance: Equilibrium and Identification in a Large NTU matching markets with stochastic choice”.
A. Galichon, S.D. Kominers, and S. Weber (2014): “An Empirical Framework for Matching with Imperfectly Transferable Utility”.
A. Galichon, B. Salanie (2012): ” Cupid’s Invisible Hand: Social Surplus and Identification in Matching Models”.

(c) 2015 the TraME Project, led by Alfred Galichon. Implementation in R. Requires Gurobi. This software may be used for non-commercial use only and comes with absolutely no warranty.