Amsterdam Econometrics Seminars and Workshop Series

Aureo de Paula (University College London, United Kingdom and Sao Paulo School of Economics, Brazil)
Friday, 3 June 2016

This paper provides a framework for identifying preferences in a large network under the assumption of pairwise stability of network links. Network data present difficulties for identification, especially when links between nodes in a network can be interdependent: e.g., where indirect connections matter. Given a preference specifi cation, we use the observed proportions of various possible payo -relevant local network structures to learn about the underlying parameters. We show how one can map the observed proportions of these local structures to sets of parameters that are consistent with the model and the data. Our main result provides necessary conditions for parameters to belong to the identfi ed set, and this result holds for a wide class of models. We also provide sucient conditions|and hence a characterization of the identifi ed set|for two empirically relevant classes of specifi cations. An interesting feature of our approach is the use of the economic model under pairwise stability as a vehicle for eff ective dimension reduction. The paper then provides a quadratic programming algorithm that can be used to construct the identfii ed sets. This algorithm is illustrated with a pair of simulation exercises. Joint with Seth Richards-Shubikz (Carnegie Mellon University and NBER, United States) and Elie Tamer (Harvard University, United States)

Link to paper