Hurdle Model

How it works

Highlighted claims

• The hurdle model separates edge presence from conditional positive edge strength. — A Bayesian Adaptive Latent Mixture Model for Zero-Inflated Weighted Brain Connectome Analysis
• The presence probability is modeled as a logistic function of a global intercept and the latent edge mean. — A Bayesian Adaptive Latent Mixture Model for Zero-Inflated Weighted Brain Connectome Analysis
• The coupling parameter determines whether absent edges are informative about weak latent connectivity. — A Bayesian Adaptive Latent Mixture Model for Zero-Inflated Weighted Brain Connectome Analysis
• Conditional nonzero weights are modeled with a Gaussian likelihood, with a Student-t alternative available for robustness. — A Bayesian Adaptive Latent Mixture Model for Zero-Inflated Weighted Brain Connectome Analysis