Significant differences

You might want to use your knowledge of t-tests and summary statistics to determine whether there are significant differences between multiple sets of predictions. Say, for example, that you wanted to know with statistical certainty whether one set of predictions was more accurate than another. You could start by computing absolute deviations, taking the absolute value of the differences between predicted and actual final grades. Recall that higher average absolute deviation means less accurate predictions.

You can also compute summary statistics and perform a t-test on these absolute deviations to determine which set of predictions has more variation (i.e., higher absolute deviation) and whether the difference between groups is statistically significant.