Longitudinal network models and permutation‐uniform Markov chains

We offer a general approach to modeling longitudinal network data, including exponential random graph models (ERGMs), that vary according to certain discrete-time Markov chains. We connect conditional and Markovian exponential families, permutation-uniform Markov chains, various (temporal) ERGMs, and statistical considerations such as dyadic independence and exchangeability. By removing models’ temporal dependence but not interpretability, our approach simplifies analysis of some network and autoregressive models from the literature, including closed-form expressions for maximum likelihood estimators. We also introduce exponential random t-multigraph models, motivated by our result on replacing t observations of permutation-uniform Markov chains of graphs with single observations of corresponding multigraphs.

[1]  T. Snijders.  The statistical evaluation of social network dynamics , 2001 .

[2]  Stephen E. Fienberg,et al.  Statistical Inference in a Directed Network Model With Covariates , 2016, Journal of the American Statistical Association.

[3]  P. Pattison,et al.  New Specifications for Exponential Random Graph Models , 2006 .

[4]  Pavel N Krivitsky,et al.  A separable model for dynamic networks , 2010, Journal of the Royal Statistical Society. Series B, Statistical methodology.

[5]  Edoardo M. Airoldi,et al.  A Survey of Statistical Network Models , 2009, Found. Trends Mach. Learn..

[6]  Stephen E. Fienberg,et al.  Maximum likelihood estimation in log-linear models , 2011, 1104.3618.

[7]  P. Diaconis,et al.  Estimating and understanding exponential random graph models , 2011, 1102.2650.

[8]  Steven M. Goodreau,et al.  Advances in exponential random graph (p*) models applied to a large social network , 2007, Soc. Networks.

[9]  K. Yasutomi,et al.  Realization of an ergodic Markov chain as a random walk subject to a synchronizing road coloring , 2011 .

[10]  Eric D. Kolaczyk,et al.  Topics at the Frontier of Statistics and Network Analysis: (Re)Visiting the Foundations , 2017 .

[11]  A. Rinaldo,et al.  Random networks, graphical models and exchangeability , 2017, 1701.08420.

[12]  Mark C. Parsons,et al.  Social networks: Evolving graphs with memory dependent edges , 2011 .

[13]  P. Feigin.  Conditional Exponential Families and a Representation Theorem for Asympotic Inference , 1981 .

[14]  Persi Diaconis,et al.  Iterated Random Functions , 1999, SIAM Rev..

[15]  L. Breuer.  Introduction to Stochastic Processes , 2022, Statistical Methods for Climate Scientists.

[16]  Dawn Iacobucci,et al.  Sequential social network data , 1988 .

[17]  Allan Sly,et al.  Random graphs with a given degree sequence , 2010, 1005.1136.

[18]  Eric D. Kolaczyk,et al.  Statistical Analysis of Network Data with R , 2020, Use R!.

[19]  M. Newman,et al.  Solution of the two-star model of a network. , 2004, Physical review. E, Statistical, nonlinear, and soft matter physics.

[20]  Alessandro Rinaldo,et al.  On Exchangeability in Network Models , 2017, Journal of Algebraic Statistics.

[21]  Peter D. Hoff,et al.  MULTILINEAR TENSOR REGRESSION FOR LONGITUDINAL RELATIONAL DATA. , 2014, The annals of applied statistics.

[22]  M. Hallinan,et al.  A Stochastic Model for Change in Group Structure , 1976 .

[23]  Ove Frank,et al.  http://www.jstor.org/about/terms.html. JSTOR's Terms and Conditions of Use provides, in part, that unless you have obtained , 2007 .

[24]  Peter Grindrod,et al.  Evolving graphs: dynamical models, inverse problems and propagation , 2010, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[25]  D. L. Hanson.  On the representation problem for stationary stochastic processes with trivial tail field , 1962 .

[26]  L. Katz,et al.  The concept of configuration of interpersonal relations in a group as a time-dependent stochastic process , 1959 .

[27]  J. Mielniczuk,et al.  A new look at measuring dependence , 2010 .

[28]  J. Gani,et al.  SOME THEOREMS AND SUFFICIENCY CONDITIONS FOR THE MAXIMUM-LIKELIHOOD ESTIMATOR OF AN UNKNOWN PARAMETER IN A SIMPLE MARKOV CHAIN , 1955 .

[29]  Michael I. Jordan,et al.  Graphical Models, Exponential Families, and Variational Inference , 2008, Found. Trends Mach. Learn..

[30]  I. Hudson.  Large Sample Inference for Markovian Exponential Families with Application to Branching Processes with Immigration , 1982 .

[31]  Murray Rosenblatt,et al.  Stationary Processes as Shifts of Functions of Independent Random Variables , 1959 .

[32]  Nial Friel,et al.  Choosing the number of groups in a latent stochastic blockmodel for dynamic networks , 2017, Network Science.

[33]  Sonja Petrovic,et al.  A survey of discrete methods in (algebraic) statistics for networks , 2015, ArXiv.

[34]  B.L.S. Prakasa Rao,et al.  Exponential Families of Stochastic Processes , 2019, Semimartingales and their Statistical Inference.

[35]  W. Rudin.  Principles of mathematical analysis , 1964 .

[36]  Erling B. Andersen,et al.  Sufficiency and Exponential Families for Discrete Sample Spaces , 1970 .

[37]  B. Graham.  An Econometric Model of Network Formation With Degree Heterogeneity , 2017 .

[38]  V. Stefanov.  Explicit Limit Results for Minimal Sufficient Statistics and Maximum Likelihood Estimators in Some Markov Processes: Exponential Families Approach , 1995 .

[39]  V. T. Stefanov.  Noncurved exponential families associated with observations over finite state Markov chains , 1991 .

[40]  M. M. Meyer,et al.  Statistical Analysis of Multiple Sociometric Relations. , 1985 .

[41]  Robert L. Wolpert,et al.  Statistical Inference , 2019, Encyclopedia of Social Network Analysis and Mining.

[42]  A. Rinaldo,et al.  On the geometry of discrete exponential families with application to exponential random graph models , 2008, 0901.0026.

[43]  Eric P. Xing,et al.  Discrete Temporal Models of Social Networks , 2006, SNA@ICML.

[44]  J. Denny.  Sufficient Statistics and Discrete Exponential Families , 1972 .

[45]  D. Hunter,et al.  Goodness of Fit of Social Network Models , 2008 .

[46]  Jeffrey M. Wooldridge,et al.  Introductory Econometrics: A Modern Approach , 1999 .

[47]  S. Wasserman.  Analyzing Social Networks as Stochastic Processes , 1980 .

[48]  On a class of one-sided Markov shifts , 2004, math/0406059.

[49]  O. Barndorff-Nielsen.  Information and Exponential Families in Statistical Theory , 1980 .

[50]  A. Rinaldo,et al.  CONSISTENCY UNDER SAMPLING OF EXPONENTIAL RANDOM GRAPH MODELS. , 2011, Annals of statistics.

[51]  M. Handcock.  Center for Studies in Demography and Ecology Assessing Degeneracy in Statistical Models of Social Networks , 2005 .

[52]  P. Pattison,et al.  Random graph models for temporal processes in social networks , 2001 .

[53]  E. L. Lehmann,et al.  Theory of point estimation , 1950 .

[54]  J. Gani,et al.  A note on sufficiency in regular Markov chains , 1960 .

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

[56]  I. Olkin,et al.  Inequalities: Theory of Majorization and Its Applications , 1980 .

[57]  L. Shepp.  Probability Essentials , 2002 .