Inference and model determination for Temperature-Driven non-linear Ecological Models

TL;DR

This paper introduces Bayesian statistical methods, including novel distributional assumptions and computational techniques, to model temperature effects on arthropod development rates, addressing variability and model uncertainty.

Contribution

It develops new Bayesian ecological models with alternative distributions and inference methods, enhancing robustness and flexibility in temperature-dependent developmental rate analysis.

Findings

Inverse Gamma-based models better capture variance fluctuations.

Zero Inflated Inverse Gamma model addresses no-development scenarios.

Bayesian Model Averaging improves parameter estimation robustness.

Abstract

This paper is concerned with a contemporary Bayesian approach to the effect of temperature on developmental rates. We develop statistical methods using recent computational tools to model four commonly used ecological non-linear mathematical curves that describe arthropods' developmental rates. Such models address the effect of temperature fluctuations on the developmental rate of arthropods. In addition to the widely used Gaussian distributional assumption, we also explore Inverse Gamma--based alternatives, which naturally accommodate adaptive variance fluctuation with temperature. Moreover, to overcome the associated parameter indeterminacy in the case of no development, we suggest the Zero Inflated Inverse Gamma model. The ecological models are compared graphically via posterior predictive plots and quantitatively via Marginal likelihood estimates and Information criteria values. Inference is performed using the Stan software and we investigate the statistical and computational efficiency of its Hamiltonian Monte Carlo and Variational Inference methods. We explore model uncertainty and use Bayesian Model Averaging framework for robust estimation of the key ecological parameters