Many national science frameworks (e.g., Next Generation Science Standards) argue that developing mathematical modeling competencies is critical for students' deep understanding of science. However, science teachers may be unprepared to assess these competencies. We are addressing this need by developing virtual lab performance assessments that assess these competencies in science inquiry contexts. Through our design processes, we developed a method for validating the assessments that takes advantage of the unique opportunities afforded by collecting log data. Here, we describe this method and demonstrate its utility by analyzing students' competencies with one example sub-practice of mathematical modeling, "plotting controlled data generated from a simulation." [This is a paper in: M. M. Rodrigo et al. (Eds.): AIED 2022, LNCS 13356, (pp. 488--491), 2022.]