An important practice is to check the validity of any data setthat you analyze. One goal is to detect typos in the data, andanother would be to detect faulty measurements. Recall thatoutliers are observations with values outside the “normal” range ofvalues of the rest of the observations.
Specify a large population that you might want to studyand describe the type numeric measurement that you will collect(examples: a count of things, the height of people, a score on asurvey, the weight of something). What would you do if you found acouple outliers in a sample of size 100? What would you do if youfound two values that were twice as big as the next highestvalue?
You may use examples from your area of interest, such as monthlysales levels of a product, file transfer times to differentcomputer on a network, characteristics of people (height, time torun the 100 meter dash, statistics grades, etc.), trading volume ona stock exchange, or other such things.
