One of the critical challenges in demand response is to calculate the customer baseline load, and it can be particularly challenging for residential demand response where each household's daily electricity load can vary randomly and significantly. A general and widely accepted enhancement method for customer baseline load is to set up an independent control group, but it requires a careful selection process and exclusion of the selected customers. In this paper, we propose the concept of virtual control group that can provide the benefits of control group without requiring the main burdens. A virtual control group is adaptively formed for each demand response event using the pre-collected participation information (through a mobile app in our pilot program), and it can perform well when used with difference-in-differences that can handle the selection bias. The customer baseline load calculation method that combines virtual control group and difference-in-differences is named as V-CBL in this study. Using a real-world dataset collected from a pilot residential demand response program, we evaluate V-CBL's robustness against selection bias and assess V-CBL's mean error performance and mean absolute error performance against the traditional models. Besides the analysis based on the non-event days, we provide an analysis on the actual DR event days as well.