Paper detail

Optimal Study Design for Reducing Variances of Coefficient Estimators in Change-Point Models

In longitudinal studies, we observe measurements of the same variables at different time points to track the changes in their pattern over time. In such studies, scheduling of the data collection waves (i.e. time of participants' visits) is often pre-determined to accommodate ease of project management and compliance. Hence, it is common to schedule those visits at equally spaced time intervals. However, recent publications based on simulated experiments indicate that the power of studies and the precision of model parameter estimators is related to the participants' visiting schemes. In this paper, we consider the longitudinal studies that investigate the changing pattern of a disease outcome, (e.g. the accelerated cognitive decline of senior adults). Such studies are often analyzed by the broken-stick model, consisting of two segments of linear models connected at an unknown change-point. We formulate this design problem into a high-dimensional optimization problem and derive its analytical solution. Based on this solution, we propose an optimal design of the visiting scheme that maximizes the power (i.e. reduce the variance of estimators) to identify the onset of accelerated decline. Using both simulation studies and evidence from real data, we demonstrate our optimal design outperforms the standard equally-spaced design. Applying our novel design to plan the longitudinal studies, researchers can improve the power of detecting pattern change without collecting extra data.