Assessment and Selection of Competing Models for Zero-Inflated Microbiome Data

TLDR

Microbiome studies generate OTU count data with excess zeros that are frequently ignored by researchers. This study compares the performance of competing zero‑inflated modeling approaches through extensive simulations and a real gut microbiome application. The authors evaluate standard parametric, non‑parametric, hurdle, and zero‑inflated models across varying degrees of zero inflation, dispersion, and covariate effects, assessing type I error, power, fit, bias, and model‑selection criteria such as AIC and Vuong, and apply the framework to a >400‑subject gut microbiome cohort. Results show that hurdle and zero‑inflated models maintain well‑controlled type I error, higher power, superior fit, and more accurate parameter estimates, with hurdle models offering comparable count‑component performance but differing in zero‑component interpretation and greater stability when structural zeros are absent, and the proposed model‑selection strategy successfully identifies the correct model in the real data.

Abstract

Typical data in a microbiome study consist of the operational taxonomic unit (OTU) counts that have the characteristic of excess zeros, which are often ignored by investigators. In this paper, we compare the performance of different competing methods to model data with zero inflated features through extensive simulations and application to a microbiome study. These methods include standard parametric and non-parametric models, hurdle models, and zero inflated models. We examine varying degrees of zero inflation, with or without dispersion in the count component, as well as different magnitude and direction of the covariate effect on structural zeros and the count components. We focus on the assessment of type I error, power to detect the overall covariate effect, measures of model fit, and bias and effectiveness of parameter estimations. We also evaluate the abilities of model selection strategies using Akaike information criterion (AIC) or Vuong test to identify the correct model. The simulation studies show that hurdle and zero inflated models have well controlled type I errors, higher power, better goodness of fit measures, and are more accurate and efficient in the parameter estimation. Besides that, the hurdle models have similar goodness of fit and parameter estimation for the count component as their corresponding zero inflated models. However, the estimation and interpretation of the parameters for the zero components differs, and hurdle models are more stable when structural zeros are absent. We then discuss the model selection strategy for zero inflated data and implement it in a gut microbiome study of > 400 independent subjects.