
Histograms
Worksheet 1
My friend Jill has a collection
of 240 compact disks. She keeps track of them in a spread
sheet; one variable she measures and records is the
playing time. Jill (like just about every other woman)
has Joni Mitchell's Hejira in her collection; Hejira has
a playing time of 51:23 which is 51.383 minutes. Here's a
histogram.
 Note the presence of at
least one outlier. How many outliers are there?
(The exact height of the bar over the 36 class
is 0.83%.)
 Give some likely
explanations for the outlier(s).
 What percentage of Jill's
CDs have playing time between 33 and 39 minutes?
 Using the histogram it is
possible to closely approximate the value of the
96^{th} percentile. What is this value?
 Characterize the shape of
the distribution.
 Dropping the outliers from
the data set, Jill computes the mean playing time
to be 45.03 minutes. How will the median compare
to this value?
 If Jill were to include the
outlier(s), how would the mean change? How would
the median change?

