This study examined the statistical effect of changing from a 10-point to a 5-point response scale on students' evaluation of instruction. Participants were 5,616 students enrolled in classes offered by the College of Social Sciences and Public Affairs at a large Western university, who completed both the old evaluation (10-point response) and the new evaluation (5-point response). On average, students used a greater range of points on the scale for the 5-point scale (32 percent) than on the 10-point scale (19 percent). The effects of changing the response scale are discussed.