Networks consist of interconnected units known as nodes that capture interactions within a system. Bipartite networks specifically depict relationships between two distinct sets of nodes, designated as sending and receiving nodes. An integral aspect of bipartite network analysis often involves identifying clusters of nodes with similar behaviors. The computational complexity of modeling large bipartite networks poses a challenge. To mitigate this challenge, we employ a Mixture of Latent Trait Analyz- ers (MLTA) for node clustering. Our approach extends MLTA to include covariates, accounting for nodal attributes, and introduces a double EM algorithm for esti- mation. Applying our method to COVID-19 data, with sending nodes representing patients and receiving nodes representing preventive measures, enables dimension- ality reduction and the identification of meaningful groups. We present simulation results demonstrating the accuracy of the proposed method
Finite mixtures of latent trait analyzers with concomitant variables for bipartite networks: an analysis of COVID-19 data / Failli, Dalila; Francesca Marino, Maria; Martella, Francesca. - In: MULTIVARIATE BEHAVIORAL RESEARCH. - ISSN 0027-3171. - (2024), pp. 1-36.
Finite mixtures of latent trait analyzers with concomitant variables for bipartite networks: an analysis of COVID-19 data
Francesca Martella
2024
Abstract
Networks consist of interconnected units known as nodes that capture interactions within a system. Bipartite networks specifically depict relationships between two distinct sets of nodes, designated as sending and receiving nodes. An integral aspect of bipartite network analysis often involves identifying clusters of nodes with similar behaviors. The computational complexity of modeling large bipartite networks poses a challenge. To mitigate this challenge, we employ a Mixture of Latent Trait Analyz- ers (MLTA) for node clustering. Our approach extends MLTA to include covariates, accounting for nodal attributes, and introduces a double EM algorithm for esti- mation. Applying our method to COVID-19 data, with sending nodes representing patients and receiving nodes representing preventive measures, enables dimension- ality reduction and the identification of meaningful groups. We present simulation results demonstrating the accuracy of the proposed methodI documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.