CDsampling: An R Package for Constrained D-Optimal Sampling in Paid Research Studies

TL;DR

The paper introduces CDsampling, an R package that implements constrained D-optimal sampling strategies for paid research and clinical trials, integrating optimal design theory with practical sampling constraints.

Contribution

It is the first package to combine constrained sampling with optimal design theories, providing both approximate and exact D-optimal allocations and robust uniform sampling options.

Findings

Demonstrates effectiveness through simulated examples.

Provides real-data case studies comparing sampling methods.

Revisits Fisher information matrix computations for various models.

Abstract

In the context of paid research studies and clinical trials, budget considerations often require patient sampling from available populations which comes with inherent constraints. We introduce the R package CDsampling, which is the first to our knowledge to integrate optimal design theories within the framework of constrained sampling. This package offers the possibility to find both D-optimal approximate and exact allocations for samplings with or without constraints. Additionally, it provides functions to find constrained uniform sampling as a robust sampling strategy when the model information is limited. To demonstrate its efficacy, we provide simulated examples and a real-data example with datasets embedded in the package and compare them with classical sampling methods. Furthermore, the package revisits the theoretical results of the Fisher information matrix for generalized linear models (including regular linear regression model) and multinomial logistic models, offering functions for its computation.