Test selection design (TSD) is an important technique improving product maintainability, reliability and reducing lifecycle costs. Three key testability metrics (TMs), fault detection rate (FDR) and fault isolation rate (FIR) and false alarm rate (FAR), are often considered to evaluate the test selection model. However, the TMs of TSD is commonly constructed only by joint distribution, which does not effectively take the correlation between test outcomes into consideration. In this study, a new approach that combines copula and D-Vine copula is proposed to address the correlation issue in TSD. First, the copula is utilized for modeling FIR on the joint distribution. And the D-Vine copula is applied to model the FDR and FAR. Then, a particle swarm optimization is employed to select the optimal testing scheme. Finally, the efficacy of the proposed method is validated through an experimentation on a negative feedback circuit.