Markov chain Monte Carlo exact inference for social networks

Abstract The uniformly most powerful unbiased test of reciprocity compares the observed number of mutual relations to its exact conditional distribution. Metropolis–Hastings algorithms have been proposed for generating from this distribution in order to perform Monte Carlo exact inference. Triad census statistics are often used to test for the presence of network group structure. We show how one of the proposed Metropolis–Hastings algorithms can be modified to generate from the conditional distribution of the triad census given the in-degrees, the out-degrees and the number of mutual dyads. We compare the results of this algorithm with those obtained by using various approximations.

[1]  J. Forster,et al.  Monte Carlo exact tests for square contingency tables , 1996 .

[2]  Stanley Wasserman,et al.  Social Network Analysis: Methods and Applications , 1994 .

[3]  David Krackhardt,et al.  Cognitive social structures , 1987 .

[4]  T. Snijders.  Enumeration and simulation methods for 0–1 matrices with given marginals , 1991 .

[5]  John C. McKinney,et al.  An Educational Application of a Two-Dimensional Sociometric Test , 1948 .

[6]  Stanley Wasserman,et al.  Random directed graph distributions and the triad census in social networks , 1977 .

[7]  Adrian F. M. Smith,et al.  Bayesian computation via the gibbs sampler and related markov chain monte carlo methods (with discus , 1993 .

[8]  P. Holland,et al.  An Exponential Family of Probability Distributions for Directed Graphs , 1981 .

[9]  P W Smith,et al.  Monte Carlo exact methods used for analysing interethnic unions in Great Britain. , 1996, Journal of the Royal Statistical Society. Series C, Applied statistics.

[10]  Samuel Leinhardt,et al.  An Omnibus Test for Social Structure Using Triads , 1978 .

[11]  W. K. Hastings,et al.  Monte Carlo Sampling Methods Using Markov Chains and Their Applications , 1970 .

[12]  A. Rao,et al.  A Markov chain Monte carol method for generating random (0, 1)-matrices with given marginals , 1996 .

[13]  John M. Roberts.  Simple methods for simulating sociomatrices with given marginal totals , 2000, Soc. Networks.

[14]  Charles J. Geyer,et al.  Practical Markov Chain Monte Carlo , 1992 .

[15]  W. Gilks.  Markov Chain Monte Carlo , 2005 .

[16]  P. Holland,et al.  A Method for Detecting Structure in Sociometric Data , 1970, American Journal of Sociology.

[17]  Stanley Wasserman,et al.  Social Network Analysis: Methods and Applications , 1994, Structural analysis in the social sciences.