CMStatistics 2020: Start Registration
View Submission - CMStatistics
B1194
Title: Network Hawkes process models for exploring latent hierarchy in social animal interactions Authors:  Owen Ward - Simon Fraser University (Canada) [presenting]
Tian Zheng - Columbia University (United States)
Anna Smith - University of Kentucky (United States)
Abstract: Group-based social dominance hierarchies are of essential interest in animal behavior research. Studies often collect aggressive interaction data observed over time, with researchers interested in understanding how the underlying social hierarchy is established and dynamically evolves. Models that capture such dynamic hierarchy are therefore crucial. Traditional ranking methods summarize interactions across time, relying only on aggregate counts. Instead, we take advantage of the interaction timestamps, proposing a series of network point process models with latent ranks. We carefully design these models to incorporate important characteristics of animal interaction data, including the winner effect, bursting and pair-flip phenomena. Through iteratively constructing and evaluating these models we arrive at the final model, utilising a cohort Markov modulated Hawkes process (C-MMHP), which best characterizes all aforementioned patterns observed in the behavior of mice cohorts. We compare all models under study using simulated and real data. Using statistically developed diagnostic perspectives, we demonstrate that the C-MMHP model outperforms other existing methods and models, recovering the underlying rankings when the ground truth is available, and capturing relevant latent ranking structures that lead to meaningful predictions.