Social Networks

Paper abstract: Permutation tests have a long history in testing hypotheses of independence between nodal attributes and network structure, though they are often thought less informative than parametric modeling techniques. In this paper, we show that when the nodal attribute is random assignment to a treatment condition, permutation tests provide a valid test of the causal effect of treatment. We discuss existing test statistics used in network permutation tests and propose several new statistics. In simulations we find that these statistics perform well compared to parametric tests and that specific statistics can be selected to provide power against common network models. We illustrate the methods with gene-wide association study performed on randomized study participants and an observational study of gender membership on Scandinavian corporate boards. This replication archive contains all materials to recreate analysis, figures, and the paper itself. See README.txt for system requirements.

Inside the code is an algorithmic framework for modeling the dynamic process of how the Venture Capital network come into being. Usage: To simulate this model, run Launcher.m with Parameter ClassANumber = 75 (original VC number); ClassBNumber = 375(original firm number); step = 14 (iteration times); Count = 10 ( times during each iteration).

Experimental data & analysis file (Stata)

Experimental data & analysis file (Stata)

Results of the laboratory experiment about the impact of referrals and information flow on hiring decisions, created by using the software z-Tree