This study attempts to understand the source of variation in the Students' Evaluation of Teaching (SET) of mathematics courses by comparing the data structure of engineering major students and mathematics major students' datasets. The sample considered in this study consists of 644 students distributed into two majors: 237 mathematics students and 407 engineering students who filled out a 20-item SET questionnaire to rate the teaching practices of three different mathematics courses offered by the Department of Mathematics. The hypothesis tested in this study is: that variation in students' perceptions of mathematics course teaching practices is different based on students' majors (Mathematics versus Engineering). Measurement invariance (MI) analyses were used to examine the source of variation in the datasets and to compare engineering and mathematics students' perceptions of the teaching effectiveness of mathematics courses. While the results of this study provide evidence of the SET validity, it was found that engineering students differently perceive three out of twenty of the SET questionnaire items when compared with mathematics major students.