The simplest way to calculate which type of student performs better in this graduate school’s classes is to find the overall average score for both types of students and then find the difference between those two averages.
|Students with work experience||Students without work experience||Difference btw average scores|
|Class||Average Score||# of students in class||Average Score||# of students in class|
|Overall Average Score||83.8||30||81.5||30||83.8 – 81.5= 2.3|
Because we’re calculating how different the work experienced student scores are from the non-work experienced scores, we get a positive number if the average score is higher for students with work experience and a negative number if their average score is lower.
So on average, using this calculation, it appears that scores for students with work experience are 2.3 points higher than math scores for students without work experience.
But wait, what if some classes are harder than others? What if some classes are taught by less effective teachers? And what if students without work experience are more likely to be in those classes? Then, it might look like those students have worse scores, when actually, they’re just working with more challenging material (or received less effective teaching). How do we adjust for these possibilities? To do that, try approach # 2