Bayesian Fractional Polynomials for Optimal Dosage Estimation with Fish Nutrition Applications

TL;DR

This paper presents a Bayesian fractional polynomial framework for accurately estimating optimal dosages in nonlinear dose-response relationships, with applications in fish nutrition and other scientific fields.

Contribution

It introduces a flexible Bayesian modeling approach that quantifies uncertainty and improves dose estimation accuracy over existing benchmarks.

Findings

BFP yields accurate dose estimates in simulations.

The method outperforms benchmark models significantly.

Demonstrated on real fish nutrition data.

Abstract

The problem of optimal dosage estimation arises in diverse scientific domains, from pharmacology and toxicology to aquaculture and environmental studies. Statistical modeling of nonlinear dose-response relationships is essential to quantify biological effects and determine response-optimal levels. This paper introduces a flexible Bayesian fractional polynomial (BFP) framework for modeling such relationships, allowing for model uncertainty quantification and robust prediction through Bayesian model averaging. Extensive simulation results demonstrate that the proposed BFP approach yields accurate estimation of optimal dose levels, outperforming benchmarks significantly. The approach is demonstrated on real data from fish nutrient requirement experiments.