arXiv subjects

Scott L. Zeger

Publications and source records attributed to Scott L. Zeger.

7 recordsLinked to original sources

arXiv2026

Validity in machine learning for extreme event attribution

Extreme event attribution (EEA), which assesses the extent to which disasters are caused by climate change, is crucial for informing climate policy and legal proceedings. Machine learning is increasingly used for EEA by modeling rare weather events too complex or computationally intensive for traditional methods. However, its validity remains unclear, as machine learning applications are criticized for bias and lack of robustness. Here we evaluate machine learning for EEA using California wildfire data from 2003-2020. We identify three major threats to validity: (1) individual event attribution estimates are highly sensitive to algorithmic design choices; (2) common performance metrics like Brier score are not strongly correlated with attribution error, facilitating suboptimal model selection; and (3) distribution shift across climate scenarios substantially degrades predictive performance. We propose a more robust attribution analysis using aggregate estimates and additional evaluation metrics for predictive performance and distribution shift.

stat.AP↗

arXiv2025

PDA in Action: Ten Principles for High-Quality Multi-Site Clinical Evidence Generation

Background: Distributed Research Networks (DRNs) offer significant opportunities for collaborative multi-site research and have significantly advanced healthcare research based on clinical observational data. However, generating high-quality real-world evidence using fit-for-use data from multi-site studies faces important challenges, including biases associated with various types of heterogeneity within and across sites and data sharing difficulties. Over the last ten years, Privacy-Preserving Distributed Algorithms (PDA) have been developed and utilized in numerous national and international real-world studies spanning diverse domains, from comparative effectiveness research, target trial emulation, to healthcare delivery, policy evaluation, and system performance assessment. Despite these advances, there remains a lack of comprehensive and clear guiding principles for generating high-quality real-world evidence through collaborative studies leveraging the methods under PDA. Objective: The paper aims to establish ten principles of best practice for conducting high-quality multi-site studies using PDA. These principles cover all phases of research, including study preparation, protocol development, analysis, and final reporting. Discussion: The ten principles for conducting a PDA study outline a principled, efficient, and transparent framework for employing distributed learning algorithms within DRNs to generate reliable and reproducible real-world evidence.

cs.CY↗

arXiv2022

Learning and Predicting from Dynamic Models for COVID-19 Patient Monitoring

COVID-19 has challenged health systems to learn how to learn. This paper describes the context, methods and challenges for learning to improve COVID-19 care at one academic health center. Challenges to learning include: (1) choosing a right clinical target; (2) designing methods for accurate predictions by borrowing strength from prior patients' experiences; (3) communicating the methodology to clinicians so they understand and trust it; (4) communicating the predictions to the patient at the moment of clinical decision; and (5) continuously evaluating and revising the methods so they adapt to changing patients and clinical demands. To illustrate these challenges, this paper contrasts two statistical modeling approaches - prospective longitudinal models in common use and retrospective analogues complementary in the COVID-19 context - for predicting future biomarker trajectories and major clinical events. The methods are applied to and validated on a cohort of 1,678 patients who were hospitalized with COVID-19 during the early months of the pandemic. We emphasize graphical tools to promote physician learning and inform clinical decision making.

stat.AP↗

arXiv2019

A hierarchical model for estimating exposure-response curves from multiple studies

Cookstove replacement trials have found mixed results on their impact on respiratory health. The limited range of concentrations and small sample sizes of individual studies are important factors that may be limiting their statistical power. We present a hierarchical approach to modeling exposure concentrations and pooling data from multiple studies in order to estimate a common exposure-response curve. The exposure concentration model accommodates temporally sparse, clustered longitudinal observations. The exposure-response curve model provides a flexible, semi-parametric estimate of the exposure-response relationship while accommodating heterogeneous clustered data. We apply this model to data from three studies of cookstoves and respiratory infections in children in Nepal, which represent three study types: crossover trial, parallel trial, and case-control study. We find evidence of increased odds of disease for particulate matter concentrations between 50 and 200 $μ$g/m$^3$ and a flattening of the exposure-response curve for higher exposure concentrations. The model we present can incorporate additional studies and be applied to other settings.

stat.AP↗

arXiv2018

A Bayesian Approach to Restricted Latent Class Models for Scientifically-Structured Clustering of Multivariate Binary Outcomes

In this paper, we propose a general framework for combining evidence of varying quality to estimate underlying binary latent variables in the presence of restrictions imposed to respect the scientific context. The resulting algorithms cluster the multivariate binary data in a manner partly guided by prior knowledge. The primary model assumptions are that 1) subjects belong to classes defined by unobserved binary states, such as the true presence or absence of pathogens in epidemiology, or of antibodies in medicine, or the "ability" to correctly answer test questions in psychology, 2) a binary design matrix $Γ$ specifies relevant features in each class, and 3) measurements are independent given the latent class but can have different error rates. Conditions ensuring parameter identifiability from the likelihood function are discussed and inform the design of a novel posterior inference algorithm that simultaneously estimates the number of clusters, design matrix $Γ$, and model parameters. In finite samples and dimensions, we propose prior assumptions so that the posterior distribution of the number of clusters and the patterns of latent states tend to concentrate on smaller values and sparser patterns, respectively. The model readily extends to studies where some subjects' latent classes are known or important prior knowledge about differential measurement accuracy is available from external sources. The methods are illustrated with an analysis of protein data to detect clusters representing auto-antibody classes among scleroderma patients.

stat.ME↗

arXiv2016

A Bayesian Hierarchical Model for Prediction of Latent Health States from Multiple Data Sources with Application to Active Surveillance of Prostate Cancer

In this article, we present a Bayesian hierarchical model for predicting a latent health state from longitudinal clinical measurements. Model development is motivated by the need to integrate multiple sources of data to improve clinical decisions about whether to remove or irradiate a patient's prostate cancer. Existing modeling approaches are extended to accommodate measurement error in cancer state determinations based on biopsied tissue, clinical measurements possibly not missing at random, and informative partial observation of the true state. The proposed model enables estimation of whether an individual's underlying prostate cancer is aggressive, requiring surgery and/or radiation, or indolent, permitting continued surveillance. These individualized predictions can then be communicated to clinicians and patients to inform decision-making. We demonstrate the model with data from a cohort of low risk prostate cancer patients at Johns Hopkins University and assess predictive accuracy among a subset for whom true cancer state is observed. Simulation studies confirm model performance and explore the impact of adjusting for informative missingness on true state predictions. R code and simulated data available at https://github.com/rycoley/prediction-prostate-surveillance.

stat.ME↗

arXiv2014

Partially-Latent Class Models (pLCM) for Case-Control Studies of Childhood Pneumonia Etiology

In population studies on the etiology of disease, one goal is the estimation of the fraction of cases attributable to each of several causes. For example, pneumonia is a clinical diagnosis of lung infection that may be caused by viral, bacterial, fungal, or other pathogens. The study of pneumonia etiology is challenging because directly sampling from the lung to identify the etiologic pathogen is not standard clinical practice in most settings. Instead, measurements from multiple peripheral specimens are made. This paper introduces the statistical methodology designed for estimating the population etiology distribution and the individual etiology probabilities in the Pneumonia Etiology Research for Child Health (PERCH) study of 9; 500 children for 7 sites around the world. We formulate the scientific problem in statistical terms as estimating the mixing weights and latent class indicators under a partially-latent class model (pLCM) that combines heterogeneous measurements with different error rates obtained from a case-control study. We introduce the pLCM as an extension of the latent class model. We also introduce graphical displays of the population data and inferred latent-class frequencies. The methods are tested with simulated data, and then applied to PERCH data. The paper closes with a brief description of extensions of the pLCM to the regression setting and to the case where conditional independence among the measures is relaxed.

stat.AP↗