Prompts
for Forum 2b: Evans Basic Statistics: Chapters 5-8
Here are a few additional exercises (and some additional
instruction) to go with Chapters 5-8 in Evans’ Basic Statistics Web Site.
Please complete the exercises and, briefly,
provide answers and comments on Forum 2b. You can work in groups on these
exercises.
Exercise 6:
Explain when it would make sense to report an effect
size instead of (or in addition to)
the level of significance?
When performing a statistical analysis, we are generally
looking for a statistic large enough to REJECT the Null Hypothesis at some
pre-specified significance (alpha) level (usually .05 or .01). Many journal
editors, however, insist that effect
sizes be reported, also. Why do you think they want effect sizes reported?
Exercise 7:
Suppose you recorded the order in which students turn-in a test and scores they
receive on the test. Then you computed a correlation between the students’
place in the order and their test scores and get a correlation of -0.65. What is
your interpretation? What type of correlation coefficient would you compute?
Why?
Exercise 8: A
social scientist determined, after studying several communities, from small
towns to large cities, that there was a positive correlation between the number
of single women and the number of automobile accidents. Some might argue that,
because single women spend more time on cell phones, they are more easily
distracted and, hence, are involved in more accidents. Do you agree with this
explanation? What else might lead to a positive correlation?
Exercise
9: On
a particular 5-choice, multiple choice item, a group of 56 students responded as
follows:
Choice
A |
Choice
B |
Choice
C |
Choice
D |
Choice
E |
10 |
8 |
13 |
16 |
9 |
Given
that Choice D is the correct choice, do the data in the table support a claim
that the students answering D were more knowledgeable than students who selected
other choices? Explain.
Exercise
10: Samples of freshmen, sophomore, junior, and senior college woman were
surveyed as to the color of their hair. The results were as shown below. Is
there evidence to support the statement, "The color of college women's hair
is dependent upon their level of academic classification"? How strong is
the relationship between level of academic classification and color of hair?
|
Black |
Brown |
Red |
Blond |
Freshmen |
6 |
2 |
2 |
12 |
Sophomores |
6 |
2 |
3 |
12 |
Juniors |
5 |
9 |
3 |
9 |
Seniors |
2 |
11 |
2 |
3 |