A common rule of thumb for determining how many classes to use when developing a
frequency distribution with classes is:
A) between 5 and 20 classes.
B) no fewer than 6 classes.
C) equal to 0.25 times the number of data values.
D) at least 10 classes.
The American College Health Association produced the National College Health
Assessment (Andy Gardiner, “Surfacing from Depression,” February 6, 2006). The
assessment indicates that the percentage of U.S. college students who report having
been diagnosed with depression has risen from 2000. The assessment surveyed 47,202
students at 74 campuses. It discovered that 10.3% and 14.9% of students indicated that
they had been diagnosed with depression in 2000 and 2004, respectively. Assume that
half of the students surveyed were surveyed in 2004.
Conduct a hypothesis test to determine if there has been more than a 0.04 increase in
the proportion of students who indicated they have been diagnosed with depression.
Use a significance level of 0.05 and a p-value approach to this test.
A) Since p-value = 0.065 > 0.05, do not reject H0. There is not sufficient evidence to
conclude that there has been more than a 0.04 increase in the proportion of students that
indicate they have been diagnosed with depression.
B) Since p-value = 0.025 < 0.05, reject H0. There is sufficient evidence to conclude that
there has been more than a 0.04 increase in the proportion of students that indicate they
have been diagnosed with depression.