The use of of the Automatic Interaction Detector (program AID3 of the OSIRIS statistical package) to study a university program is discussed. The performance of students who took general physics lecture and laboratory concurrently is compared to the performance of those who took them separately. Five years of data are analyzed, covering 1,997 students. The educational outcomes investigation uses the AID3 program to examine a variety of independent variables, including Scholastic Aptitude Test (SAT) scores, physics lecture grade, student major, student level, high school rank, and student sex. The AID3 analysis indicates that the importance of the concurrent laboratory depends strongly on when in the analysis it is considered. The demographic measures that make a difference in explaining grades in physics class include: overall grade average, SAT math score, high school rank, and the year in which the student took the course. Finally, some nonadditive interactions occur in the data. It is demonstrated that the research method allows researchers to consider a large number of variables as possible explainers of course performance without making the restrictive assumptions required by other techniques. (SW)