Testing for Differences in Stochastic Network Structure

Abstract

How can one determine whether a community-level treatment, such as the introduction of a social program or trade shock, alters agents' incentives to form links in a network? This paper proposes analogues of a two-sample Kolmogorov-Smirnov test, widely used in the literature to test the null hypothesis of "no treatment effects", for network data. It first specifies a testing problem in which the null hypothesis is that two networks are drawn from the same random graph model. It then describes two randomization tests based on the magnitude of the difference between the networks' adjacency matrices as measured by the $2\to2$ and $\infty\to1$ operator norms. Power properties of the tests are examined analytically, in simulation, and through two real-world applications. A key finding is that the test based on the $\infty\to1$ norm can be substantially more powerful than that based on the $2\to2$ norm for the kinds of sparse and degree-heterogeneous networks common in economics.