An Empirical Method for Analyzing Count Data

2026-01-23

AI Summary

This study addresses numerical instability and reduced efficiency in covariate adjustment that arise when applying negative binomial regression under sparse event settings due to potential model misspecification. To overcome these limitations, the authors propose a marginal empirical likelihood approach that avoids imposing distributional assumptions on the count outcome. This method directly models the event rate ratio between groups while incorporating baseline covariates to enhance estimation efficiency. The proposed estimator maintains the benefits of covariate adjustment while substantially improving numerical stability and robustness in sparse data scenarios. Simulation studies demonstrate well-controlled Type I error rates and statistical power comparable to negative binomial regression. Application to the QWINT-5 clinical trial yields more stable and empirically plausible rate ratio estimates, closely aligning with observed event counts.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Other Foundations of Reasoning under Uncertainty
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Count endpoints are common in clinical trials, particularly for recurrent events such as hypoglycemia. When interest centers on comparing overall event rates between treatment groups, negative binomial (NB) regression is widely used because it accommodates overdispersion and requires only event counts and exposure times. However, NB regression can be numerically unstable when events are sparse, and the efficiency gains from baseline covariate adjustment may be sensitive to model misspecification. We propose an empirical method that targets the same marginal estimand as NB regression -- the ratio of marginal event rates -- while avoiding distributional assumptions on the count outcome. Simulation studies show that the empirical method maintains appropriate Type I error control across diverse scenarios, including extreme overdispersion and zero inflation, achieves power comparable to NB regression, and yields consistent efficiency gains from baseline covariate adjustment. We illustrate the approach using severe hypoglycemia data from the QWINT-5 trial comparing insulin efsitora alfa with insulin degludec in adults with type 1 diabetes. In this sparse-event setting, the empirical method produced stable marginal rate estimates and rate ratios closely aligned with observed rates, while NB regression exhibited greater sensitivity and larger deviations from the observed rates in the sparsest intervals. The proposed empirical method provides a robust and numerically stable alternative to NB regression, particularly when the number of events is low or when numerical stability is a concern.

Problem

• count data
• negative binomial regression
• sparse events
• numerical instability
• overdispersion

Innovation

• empirical method
• negative binomial regression
• count data
• marginal rate ratio
• sparse events