The Exam Statistics: The Mean

With the first round of (multiple-choice) midterms over, I'm now swimming in data. I want to tell you about some of the stats I go through to assess and improve my exams. Unfortunately, I'm too late to celebrate (the first) World Statistics Day. But I don't feel too bad. At least statistics has a day. It's not like there's a "Psychology Month" or anything. Oh, look--yes there is. And I'm late for that, too. Moving on...

This installment is about the (arithmetic) mean, or, if you insist, the "average." I post the class mean of every exam because you demanded it! Really, though--what use is it to you? For classes that don't grade on the curve, you don't need to know the mean (or standard deviation) to determine your absolute standing in the class. Just take your percentage correct, and see what grade that corresponds to in the syllabus. Right?

Yes, that's important. But don't you want to know how everyone else did, too? Sure you do. "Did everyone think that exam was a killer, or just me?" We want to compare ourselves to other people. Some students even want to know what the top score was. "Did anyone get 100%?" "Am I the best in the class?"

The mean also serves another purpose, when there are multiple forms of an exam. In larger classes, multiple forms of an exam are used to discourage cheating (or at least, to make it more difficult). Typically, there is one form that has the questions arranged in order of topics (e.g., questions based on the first lecture and textbook chapter first, followed by questions on the second lecture and chapter, etc.). The other forms will have the questions in a random order. Are students who get the scrambled forms at a disadvantage? Or, put another way, is there a benefit to answering questions in a sequence that reflects the arrangement of the learning materials? If so, that wouldn't be fair, would it?

The data from every exam includes the means from each form. They are usually a little bit different. But is that difference a fluke, or is it due to the ordering of questions? Hmm, sound like a job for...statistics! The data also includes the results of an ANOVA (analysis of variance) that compares the means to each other. That is, are any differences statistically significant? The answer: No. I've never had a difference at p < 0.01 or even p < 0.05. That means any differences are small; they are due to chance.

The bottom line: It doesn't matter which form you get. Isn't science cool?

Why aren't you studying?


John Outlier said...

But what if I am one of one those rare people that would have done better with one form rather than the other? What if I am one of those rare people who could do better if the information were organized sequentially rather than random? What if I am one of those outliers that are sometimes completely thrown out in statistics? I could have scored 90% higher!

I believe you owe me 90%.

Karsten Loepelmann said...

@John Outlier (is that French?): And just think what your mark would be if all the exam questions were based only on the stuff you studied?

Anonymous said...

Oh man, if all the questions were based only on the stuff I studied, that exam couldn't exist.

Find It