This article was posted by Adrian Sampson on his own blog. Adrian is an assistant professor in the Department of Computer Science at Cornell University, where here is also part of the Computer Systems Laboratory.
Computer scientists in systemsy fields, myself included, aren’t great at using statistics. Maybe it’s because there are so many other potential problems with empirical evaluations that solid statistical reasoning doesn’t seem that important. Other subfields, like HCI and machine learning, have much higher standards for data analysis. Let’s learn from their example.
Here are three kinds of avoidable statistics mistakes that I notice in published papers.
1. No Statistics at All
The most common blunder is not using statistics at all when your paper clearly uses statistical data. If your paper uses the phrase “we report the average time over 20 runs of the algorithm,” for example, you should probably use statistics.
Here are two easy things that every paper should do when it deals with performance data or anything else that can randomly vary:
First, plot the error bars. In every figure that represents an average, compute the standard error of the mean or just the plain old standard deviation and add little whiskers to each bar. Explain what the error bars mean in the caption.
Second, do a simple statistical test. If you ever say “our system’s average running time is X seconds, which is less than the baseline running time of Y seconds,” you need show that the difference is statistically significant. Statistical significance tells the reader that the difference you found was more than just “in the noise.”
Other topics in the article include:
2. Failure to Reject = Confirmation
3. The Multiple Comparisons Problem
To read more, click here.
Top DSC Resources