CHAPTER 4C: NUMERICAL DESCRIPTIVE TECHNIQUES
TRUE/FALSE
1. Statisticians typically apply graphical techniques as a first step in a data analysis because we first need
to know the shape of the distribution.
2. Graphical and numerical techniques, such as histograms and least squares lines provide identical
information.
3. The coefficient of correlation and the least squares line both describe the relationship between two
interval variables.
4. The precision provided by the numerical techniques (mean, median, and standard deviation) provides
more useful information than graphical techniques (histograms and box plots) alone.
MULTIPLE CHOICE
1. Which of the following characteristics does a histogram help you identify?
a.
The shape of distribution.
b.
The approximate center of a distribution.
c.
The amount of spread in a distribution.
d.
All of these choices are true.
2. The shape of a distribution helps answer which question about the data?
a.
Where is the approximate center of the distribution?
b.
Are the observations close to one another, or are they widely dispersed?
c.
Is the distribution symmetric?
d.
All of these choices are true.
3. Which of the following is correct about the shape of a distribution?
a.
The shape can show you how many modes there are.
b.
The shape can help you determine the approximate center of the distribution.
c.
The shape can help you determine whether the data are close or spread out.
d.
All of these choices are true.
4. A scatter diagram reveals a strong positive linear relationship between oil and gasoline prices. Which
of the following numerical techniques will not give us more detailed information about this
relationship?
a.
Coefficient of determination
b.
Coefficient of correlation
c.
Coefficient of variation.
d.
All of these choices help us describe this relationship.
COMPLETION
1. Scatter diagrams, covariance, and the coefficient of correlation are useful techniques for detecting
relationships between two ____________________ variables.
2. Statisticians usually apply graphical techniques as a first step in analyzing data because we first need
to know the ____________________ of the distribution.
3. Box plots and medians work well to describe ____________________ data, while histograms and
means work well to describe ____________________ data.
4. ____________________ techniques give you the big picture of a distribution and
____________________ techniques give you more precise details.
5. We can frequently make several inferences about the nature of the data from the
____________________ of its histogram.
SHORT ANSWER
1. What statistics and graphs can you use to answer the following question: Where is the approximate
center of the distribution?
2. What statistics and graphs can you use to answer the following question: Are the observations close to
one another, or are they widely dispersed?
3. What statistics and graphs can you use to answer the following questions: Is the distribution unimodal,
bimodal, or multimodal? If there is more than one mode, where are the peaks, and where are the
valleys?
4. What statistics and graphs can you use to answer the following question: Is the distribution symmetric?
If not, is it skewed? If symmetric, is it bell shaped?
5. What statistics and graphs can you use to look for a relationship between two interval variables?