Pseudo-value regression of clustered multistate current status data with informative cluster sizes

TL;DR

This paper develops a pseudo-value regression method to analyze clustered multistate current status data with informative cluster sizes, addressing bias caused by the relationship between cluster sizes and transition outcomes.

Contribution

It extends pseudo-value approaches to handle informative cluster sizes in multistate current status data, combining nonparametric estimation with reweighting techniques.

Findings

Simulation studies demonstrate the method's robustness under various scenarios.

Application to periodontal disease data illustrates practical utility.

Adjusted estimates reduce bias compared to traditional methods.

Abstract

Multistate current status (CS) data presents a more severe form of censoring due to the single observation of study participants transitioning through a sequence of well-defined disease states at random inspection times. Moreover, these data may be clustered within specified groups, and informativeness of the cluster sizes may arise due to the existing latent relationship between the transition outcomes and the cluster sizes. Failure to adjust for this informativeness may lead to a biased inference. Motivated by a clinical study of periodontal disease (PD), we propose an extension of the pseudo-value approach to estimate covariate effects on the state occupation probabilities (SOP) for these clustered multistate CS data with informative cluster or intra-cluster group sizes. In our approach, the proposed pseudo-value technique initially computes marginal estimators of the SOP utilizing nonparametric regression. Next, the estimating equations based on the corresponding pseudo-values are reweighted by functions of the cluster sizes to adjust for informativeness. We perform a variety of simulation studies to study the properties of our pseudo-value regression based on the nonparametric marginal estimators under different scenarios of informativeness. For illustration, the method is applied to the motivating PD dataset, which encapsulates the complex data-generation mechanism.