Abstract
High-throughput screening (HTS) assays are pivotal in modern biomedical research, particularly in drug discovery and functional genomics. Ensuring the quality and reliability of HTS data is critical, especially when dealing with the small sample sizes that are typical in such assays. This study explores the integration of two powerful statistical metrics-Strictly Standardized Mean Difference (SSMD) and Area Under the Receiver Operating Characteristic Curve (AUROC)-for quality control (QC) in HTS. SSMD offers a standardized, interpretable measure of effect size, while AUROC provides a threshold-independent assessment of discriminative power. By establishing the theoretical and empirical relationships between AUROC and SSMD, we demonstrate how these metrics complement each other and enhance QC practices. We provide parametric, semi-parametric, and non-parametric estimation methods, and demonstrate the utility of the integrated framework in real HTS datasets. Our findings support the joint application of SSMD and AUROC as a robust and interpretable approach to improving QC in HTS, particularly under constraints of limited sample sizes of positive and negative controls.