Question: In the process of selecting students for a graduate program, two faculty members read the letters of recommendation in each student’s file. Each faculty member rates the letters on a scale of 1 (poor) to 10 (outstanding). The ratings for 12 applicants follow. Assume the ratings are ordinal-level measurements at best. What is the correlation between the judges’ ratings? Is it significant? What does your decision mean in the context of the exercise?