Abstract

Biomass data for low information species can be extremely zero-inflated, where the percentage of zeros can be over 90%. This poses a challenge even for standard statistical models that naturally allow for a probability mass at zero with continuous non-negative values. We integrate data sourced from fisheries and surveys to investigate models that can be used to estimate the biomass density of low information species with zero inflation.
Despite their significance, research on zero-inflated models has predominantly focused on count models such as zero-inflated Poisson or negative binomial regressions. Such models are not suitable for biomass data which are semi-continuous. In such cases, hurdle models are commonly used. The zero-inflated (ZI) Tweedie model is emerging as a suitable model for zero-inflated semi-continuous data. The ZI Tweedie model is a mixture model that integrates a Tweedie model with a binary model to distinguish between excess zeros - those resulting from an independent process, and true zeros - those resulting from the Tweedie model itself. We use a Bayesian approach to estimate the model parameters.