In this exercise we see how the default setting in the Minitab boxplot command can be misleading, since it doesn’t take the sample size into account. We will generate three samples of different sizes from the same distribution, and compare their Minitab boxplots. Generate 250 normal (0, 1) observations and put them in column c1 by pulling down the calc menu to the random data command over to normal and filling in the dialog box. Generate 1000 normal

(0, 1) observations the same way and put them in column c2, and generate 4000 normal (0, 1) observations the same way and put them in column c3. Stack these three columns by pulling down the manip menu down to stack/unstack and over to stack columns and filling in the dialog box to put the stacked column into c4, with subscripts into c5. Form stacked boxplots by pulling down graph menu to boxplot command and filling in dialog box. Y is c4 and x is c5.

(a) What do you notice from the resulting boxplot?

(b) Which sample seems to have a heavier tail?

(c) Why is this misleading?

(d) Redo the boxplot highlighting the outlier symbol in the dialog box, and clicking on edit attributes and select dot.

(e) Is the graph still as misleading as the original?