ALAAMEE: Open-source software for fitting autologistic actor attribute models

The autologistic actor attribute model (ALAAM) is a model for social influence, derived from the more widely known exponential-family random graph model (ERGM). ALAAMs can be used to estimate parameters corresponding to multiple forms of social contagion associated with network structure and actor covariates. This work introduces ALAAMEE, open-source Python software for estimation, simulation, and goodness-of-fit testing for ALAAM models. ALAAMEE implements both the stochastic approximation and equilibrium expectation (EE) algorithms for ALAAM parameter estimation, including estimation from snowball sampled network data. It implements data structures and statistics for undirected, directed, and bipartite networks. We use a simulation study to assess the accuracy of the EE algorithm for ALAAM parameter estimation and statistical inference, and demonstrate the use of ALAAMEE with empirical examples using both small (fewer than 100 nodes) and large (more than 10 000 nodes) networks.Author summary: If we observe a social network, along with some attributes of the actors within it, including an opinion, behaviour, or belief (we will call this the outcome attribute) that we might suppose to be socially contagious, how might we test this supposition? The situation is complicated by the fact that, if the outcome attribute is indeed socially contagious, then its value for one actor will depend on its value for that actor’s network neighbours (friends, for instance). Even further complexity arises if we suppose that the outcome is not simply contagious like a disease, where it is likely to be transmitted from a single network neighbour, but its adoption might instead depend on particular patterns of adoption of the outcome attribute in the local network structure surrounding an actor. The “autologistic actor attribute model” (ALAAM) is a statistical model that, unlike some better-known models, can handle such situations. In this work we describe open-source software called ALAAMEE that implements this model, and demonstrate its use on both small and large networks.