Marginal Regression on Transient State Occupation Probabilities with Clustered Multistate Process Data

TL;DR

This paper introduces a novel nonparametric regression method for analyzing transient state occupation probabilities in clustered multistate process data, applicable in clinical studies, without relying on restrictive assumptions.

Contribution

It develops a weighted functional GEE approach that handles within-cluster dependence and informative cluster sizes, with proven asymptotic properties and hypothesis testing procedures.

Findings

Method performs well with few clusters

Ignoring dependence leads to invalid inferences

Applied to clinical trial data successfully

Abstract

Clustered multistate process data are commonly encountered in multicenter observational studies and clinical trials. A clinically important estimand with such data is the marginal probability of being in a particular transient state as a function of time. However, there is currently no method for nonparametric marginal regression analysis of these probabilities with clustered multistate process data. To address this problem, we propose a weighted functional generalized estimating equations approach which does not impose Markov assumptions or assumptions regarding the structure of the within-cluster dependence, and allows for informative cluster size (ICS). The asymptotic properties of the proposed estimators for the functional regression coefficients are rigorously established and a nonparametric hypothesis testing procedure for covariate effects is proposed. Simulation studies show that the proposed method performs well even with a small number of clusters, and that ignoring the within-cluster dependence and the ICS leads to invalid inferences. The proposed method is used to analyze data from a multicenter clinical trial on recurrent or metastatic squamous-cell carcinoma of the head and neck with a stratified randomization design.