We discussed three ways to measure how spread out data is:
Range has the problem that it only depends on the most extreme data, the outliers. Interquartile range doesn’t depend on outliers. Any data that is more than \(1.5 \times IQR\) away from the box in a box-and-whisker plot is considered an outlier.
We did this workshop in class today:
We talked about standard deviation (including calculating an example by hand… which is something you won’t have to do on quizzes or tests). The important concept to understand is that standard deviation measures spread by calculating the “typical” amount data differs from the average.
After talking about standard deviation, we went over the review problems for the midterm exam on Friday.