The outputs from high-throughput biological experiments are often affected by many operational factors. Understanding how these factors affect the reproducibility of outputs is critical for designing workflows that produce replicable results. This paper develops a quantile association regression model for assessing the covariate effects of operational factors on the reproducibility of high-throughput experiments. We establish a connection between the copula-based quantile-specific odds ratio and the correspondence curve. This connection not only allows our regression framework straightforward interpretations, but also provides a new way to utilize these local association measures in the context of reproducibility. In contrast to the existing regression model for this task, the proposed method does not assume any type of dependence structure. Moreover, it can offer the flexibility of correspondence curve with presenting rigorous statistical inference on the confidence. Using simulations, we show that the proposed method is more accurate in detecting differences in reproducibility than the state-of-the-art measures of reproducibility. We also illustrate the practical utility of our method using a real data example.