arXiv subjects

Xiahui Li

Publications and source records attributed to Xiahui Li.

3 recordsLinked to original sources

arXiv2026

Constructing Contact and Connectivity Matrices for Infectious Disease Modelling

Contact (or mixing, or more generally connectivity) matrices are a fundamental component of modelling and inference for infectious disease epidemiology. Their structure and parametrisation directly accounts for the frequency of interactions between different subpopulations of individuals, as well as having the potential to encode dynamic heterogeneity in these interactions across demographic axes, space and time. Considerable research has been devoted to the structure and estimation of (components of) these matrices to help inform outbreak control and forecast disease spread. In this paper, we review the existing literature on the data types used to construct contact matrices and the methods for incorporating uncertainties and heterogeneities into them. We also highlight remaining challenges and future directions in the use of these contact matrices for epidemiological research.

stat.AP↗

arXiv2025

Advances in Approximate Bayesian Inference for Models in Epidemiology

Bayesian inference methods are useful in infectious diseases modeling due to their capability to propagate uncertainty, manage sparse data, incorporate latent structures, and address high-dimensional parameter spaces. However, parameter inference through assimilation of observational data in these models remains challenging. While asymptotically exact Bayesian methods offer theoretical guarantees for accurate inference, they can be computationally demanding and impractical for real-time outbreak analysis. This review synthesizes recent advances in approximate Bayesian inference methods that aim to balance inferential accuracy with scalability. We focus on four prominent families: Approximate Bayesian Computation, Bayesian Synthetic Likelihood, Integrated Nested Laplace Approximation, and Variational Inference. For each method, we evaluate its relevance to epidemiological applications, emphasizing innovations that improve both computational efficiency and inference accuracy. We also offer practical guidance on method selection across a range of modeling scenarios. Finally, we identify hybrid exact approximate inference as a promising frontier that combines methodological rigor with the scalability needed for the response to outbreaks. This review provides epidemiologists with a conceptual framework to navigate the trade-off between statistical accuracy and computational feasibility in contemporary disease modeling.

stat.ME↗

arXiv2024

Gradient-Based Approximate Bayesian Inference with Entropy-Optimized Summary Statistics for Compartmental Models

Recent pandemics have highlighted the critical role of infectious disease models in guiding public health decision-making, driving demand for realistic models that can provide timely answers under uncertainty. Compartmental models are widely used to capture disease dynamics, and advances in data availability, computational resources, and epidemiological understanding have allowed the development of models that incorporate detailed representations of population structure, disease progression, and intervention effects. While these improvements improve model fidelity, they also increase model complexity, leading to high-dimensional parameter spaces, intractable likelihoods, and computational challenges for fitting models to limited surveillance data in real time. Existing likelihood-free methods, such as Approximate Bayesian Computation (ABC) and Bayesian Synthetic Likelihood (BSL), have developed largely independently, each with distinct strengths and limitations. We propose an integrated three-stage framework that synthesizes advances from both likelihood-based and likelihood-free method: (1) ABC-based entropy minimization to identify low-dimensional, approximately orthogonal summary statistics; (2) BSL inference using these optimized summaries to construct tractable Gaussian approximations; and (3) Hamiltonian Monte Carlo sampling for efficient posterior exploration. Through SEIR simulation study and application to the 1978 British boarding school influenza outbreak, we demonstrate that our framework achieves reliable parameter estimation and uncertainty quantification while maintaining computational efficiency.

stat.ME↗