GLMM-Based Modeling and Monitoring Dynamic Social Network

Social network monitoring (snm) can play a significant role in everyone’s life. recent studies show the importance and increasing interests in the subject by modeling and monitoring the communications between network members over time by treating the collected observations as longitudinal data. typically, the tendency for modeling social networks, considering the dependency of an outcome variable on the covariates, is growing recently. however, these studies fail to incorporate the possible correlation between responses in the proposed models. in this paper, we use generalized linear mixed models (glmms), also referred to as random effects models, to model a social network according to the attributes of nodes in which the nodes take a role of random effect or hidden effect in modeling. in order to estimate the regression parameters, monte carlo expectation maximization (mcem) algorithm is used to maximize the likelihood function. in our simulation studies, we applied root mean square error (rmse) and standard deviation criteria to select an appropriate model for the simulated data. results indicate zero inflated poisson mixed as an appropriate model for the data. in addition, compared to the other studies, our simulation study demonstrates an improvement in the average run length (arl).