Statistical Reasoning for Everyday Life

5th Edition Bennett Solutions Manual

Visit to download the full and correct content document: https://testbankdeal.com/dow
nload/statistical-reasoning-for-everyday-life-5th-edition-bennett-solutions-manual/
 CHAPTER 7

Section 7.1
Statistical Literacy and Critical Thinking

1 A correlation exists between two variables when higher values of one

variable are consistently associated with higher values of the other
variable, or when higher values of one variable are consistently
associated with lower values of the other variable. Examples will vary.
2 A scatterplot is a graph in which paired sample data values are plotted
as points with values of one variable on the horizontal axis and values
of the other variable on the vertical axis. If there is reason to
suspect that one variable depends on the other, we plot the explanatory
variable on the horizontal axis and the response variable on the
vertical axis. The scatterplot allows us to visualize the pattern of the
points, which is helpful in trying to determine whether there is a
correlation between the
two variables.
3 A positive correlation exists when two variables increase or decrease
together. A negative correlation exists when an increase in one variable
corresponds to a decrease in the other. No correlation exists when there
is no apparent (linear) relationship between the two variables. Examples
will vary.
4 The correlation coefficient, r, is a quantitative measure of how well
the paired data values fit the pattern of a straight line. It can take
on values from –1 to 1 (inclusive). The value r = –1 indicates a perfect
(straight line) negative correlation, r = 0 means no correlation, and r
= 1 is a perfect (straight line) positive correlation.
5 This statement does not make sense. Positive correlation and negative
correlation refer to whether two variables increase together (positive)
or in opposite directions (negative), not to whether something is good
or bad. In this case, there is a negative correlation, because an
increase in exercise time leads to a decrease in resting pulse rate.
6 This statement makes sense. The negative correlation means that the two
variables move in opposite directions, so less time on social media is
associated with a higher GPA.
7 This statement does not make sense. When the points follow a nearly
straight (diagonal) line, there is a strong correlation, not a weak one.
8 This statement does not make sense. The correlation coefficient can only
be in the range from –1 to 1 (inclusive). A value of r = 1.50 must be
the result of an error in the calculations.

Concepts and Applications

9 These variables will be positively correlated because as the weight goes

up, the mailing cost will also tend to go up.
10 These variables will be uncorrelated because the weights of taxi cab
passengers do not affect the cost of the taxi cab ride and vice versa.
11 These variables will be uncorrelated because an individual’s hat size
does not affect their IQ scores and vice versa.
12 These variables will have a negative correlation because the prize money
increases for golfers who shoot lower scores.
13 These variables will be positively correlated because as the length of
the trip increases, the cost will also increase.
14 These variables will have a negative correlation because as the weight
of a car goes up, the distance it can travel on a gallon of gas goes
down.
Copyright © 2018 Pearson Education, Inc. 86
 SECTION 7.1, SEEKING CORRELATION 87

15 These variables are not correlated because an individual’s pulse rates do not
affect their score on the SAT and vice versa.
16 These variables are positively correlated because as the size of a house goes
up, the price will also tend to go up.
17 There is a strong positive correlation, with the correlation coefficient
approximately r ≈ 0.8 to 0.9.
18 An estimate of the correlation coefficient is r ≈ 0.7. Forecasts are
reasonably accurate for two days in the future. Results should be similar
for other two-week periods although the values of the temperatures could be
different. Generally, the accuracy of two-day forecasts does not depend on
the time of year, so other two-week periods of data should show a similar
pattern.
19 The given property is true. The variables x and y appear symmetrically in the
formula (so interchanging x and y does not change the formula).
20 The given property is true. If x is multiplied by a constant, it occurs in
both the numerator and denominator; so there is no overall effect.
21 The given property is not true. The sign of the correlation coefficient will
change.
22 The given property is not true. The value of the correlation coefficient will
change if the way the data values are paired is changed.
23 a)

b) From the scatterplot, there appears to be a strong negative

correlation.
c) The correlation coefficient is r = –0.959, which suggests a strong
negative correlation.
d) It appears that greater amounts of lemon imports are association with
lower crash fatality rates, but common sense suggests that there is not
really an association between those two variables.
24 a)

b) From the scatterplot, there appears to be a weak positive correlation.

c) The correlation coefficient is r = 0.561, which suggests a moderately
positive correlation.
d) Higher enrollments appear to be moderately associated with higher
numbers of burglaries.

Copyright © 2018 Pearson Education, Inc.

88 CHAPTER 7, CORRELATION AND CAUSALITY

25 a)

b) From the scatterplot, there appears to be a strong negative

correlation.
c) The correlation coefficient is r = –0.997, which suggests a strong
negative correlation.
d) As the aircraft gains altitude, the outside temperature appears to
drop.
26 a)

b) From the scatterplot, there does not appear to be a correlation

between the front repair costs and the rear repair costs.
c) The correlation coefficient is r = –0.283, which suggests only a
weak negative correlation.
d) The costs of damage to the front and rear of the cars seem to be
unrelated to each other.
27 a)

b) From the scatterplot, there does not appear to be a correlation

between brain size and IQ score.
c) The correlation coefficient is r = 0.179, which suggests only a
weak positive correlation.
d) It does not suggest that the larger the brain size, the higher the
IQ score.

Copyright © 2018 Pearson Education, Inc.

 SECTION 7.1, SEEKING CORRELATION 89

28 a)

b) From the scatterplot, there appears to be a positive correlation

between the right and left arm measurements of systolic blood pressure.
c) The correlation coefficient is r = 0.867, which suggests a strong
positive correlation.
d) If a woman’s blood pressure increases in her left arm, her blood
pressure in her right arm is also likely to increase.
29 a)

b) From the scatterplot, there appears to be a positive correlation.

c) The correlation coefficient is r = 0.947, which suggests a strong
positive correlation.
d) It appears that there is a correlation between higher opening bids and
higher winning bids, but the scatterplot shows that this is largely
influenced by the point in the upper-right corner (an outlier and
reason for further investigation, as discussed in Section 7.2).
30 a)

b) From the scatterplot, there does not appear to be a correlation between

the ages of female and male actors at the times they won Academy
Awards.
c) The correlation coefficient is r = –0.172, which suggests a weak
negative correlation.
d) The ages when females won Academy Awards are not related to the ages
when male actors won.

Copyright © 2018 Pearson Education, Inc.

90 CHAPTER 7, CORRELATION AND CAUSALITY

Section 7.2
Statistical Literacy and Critical Thinking

1 An outlier can make it appear that a correlation exists if the outlier

is far separated from the rest of the data points, as in Figure 7.9.
Outliers can mask correlations if they are located in places opposite
where the correlation would predict, as shown in Figure 7.10. Outliers
should be ignored only when there is good reason to suspect that they
represent errors in the data.
2 Two groups of data with opposite correlations (one positive, one
negative) may seem to show no correlation when grouped together.
However, this does not mean that you should always break data into
subgroups; as illustrated in the case study Fishing for Correlations,
partitioning the data into too many subgroups can produce meaningless
correlations.
3 (1) A correlation between two variables may be a coincidence. (2) Both
variables might be directly influenced by some common underlying cause.
(3) One of the variables may actually be a cause of the other.
4 No, we cannot conclude that one variable causes change in the other
variable even with a very strong correlation. Correlation by itself is
never enough to establish causality, since there are always two other
possible explanations (coincidence or a common underlying cause).
5 This statement makes sense. A CEO taking no salary is an outlier, and
the outlier can certainly make a correlation appear where there
otherwise is none.
6 This statement does not make sense. As discussed in this section, there
may be a relationship that is being masked by outliers or inappropriate
grouping of data. It’s also possible that the sample does not show a
relationship that exists in the population.
7 This statement does not make sense. There are other possible
explanations for a correlation. For example, the growing population may
have resulted in more homes with thatched roofs that encouraged the
growth of the stork population.
8 This statement does not make sense. No matter how strong the
correlation, the correlation alone still does not tell us whether
causality is involved. Example 3 in this section on the Super Bowl
indicator shows that the correlation might be a coincidence. More
commonly, it might also be due to a common underlying cause. For
example, there is a strong correlation between the number of people who
attend church and beer consumption in cities, but this certainly does
not mean that one causes the other; both are simply effects of larger
population.

Concepts and Applications

9 There is a positive correlation between the number of unregistered

handguns and the crime rate. This correlation is probably due to a
common underlying cause. Many crimes are committed with unregistered
handguns, some with no handguns. It is also possible that a rising
crime rate leads people to purchase handguns for protection.
10 There is a negative correlation that is due to coincidence.
11 There is a positive correlation that is due to a direct cause. As
students study more, they gain a better understanding of the subject and
their test scores are likely to be higher.
12 There is a positive correlation that is due to coincidence.

Copyright © 2018 Pearson Education, Inc.

 SECTION 7.2, INTERPRETING CORRELATIONS 91

13 This is a positive correlation that is probably due to a common cause, such

as the general increase in the number of cars and traffic. That is, the
increase in vehicles requires that some intersections get new lights to
control the traffic and, at the same time, the increase in vehicles is in
part responsible for the increased number of crashes.
14 There is a positive correlation between the distance and the speed.
Astronomers can explain the correlation with a direct cause.
15 There is a negative correlation that is probably due to a direct cause. As
gas prices increase, people can’t afford to drive as much or as far, so they
cut costs by driving less.
16 There is a positive correlation that is due to coincidence.
17 a) The point (0.4, 1.0) is an outlier since it lies far from the rest of
the data points. Without the outlier, there is no linear relationship
between the variables, so the correlation is zero.
b) With the outlier included, there is a negative correlation (actual
value is r = -0.58).
18 a) The point (0.5, 1.0) is an outlier. Without the outlier, there is a
strong positive correlation, probably 0.95 or larger (actual value is r
= 0.99).
b) With the outlier, the correlation is still positive, but much less than
without it (actual value is r = 0.85).
19 a) There appears to be a positive correlation (r = 0.853).
b) There appears to be a strong positive correlation (r = 0.932).
c) There is a weak negative correlation (r = ‒0.302).
d) No, the results do not make sense. It doesn’t seem reasonable that
there would be a strong positive correlation for males but a weak
negative correlation for females. Perhaps the results are affected by
the fact that the sample sizes are relatively small.
20 a) It appears that there is a strong negative correlation (actual value is
r = -0.87). Based on the correlation coefficient, yes, we would expect
that lower January temperatures would result in higher July
temperatures.

b) There does not appear to be any correlation within each of the two
groups of five cities. The correlation in part (a) is due to the fact
that summer and winter are reversed in the Northern and Southern
Hemispheres.
21 a) The correlation coefficient is r = 0.77, indicating a strong positive
correlation.
b) The points toward the right correspond to relatively poor countries,
such as Uganda, which tend to have high birth rates and high death
rates. The points toward the left correspond to relative affluent
countries, such as Sweden, which have low birth rates and low
death rates.
c) Wealthier countries have a negative correlation: Higher birth rates are
associated with lower death rates. Poorer countries have a positive
correlation: Higher birth rates are associated with higher death rates.
Copyright © 2018 Pearson Education, Inc.
92 CHAPTER 7, CORRELATION AND CAUSALITY

22 a) Yes, there appears to be a negative correlation.

b) No, there does not appear to be a linear correlation. These points
correspond to pennies that all weigh less than 2.6 grams and were
all manufactured after 1983.
c) No, there does not appear to be a linear correlation. These points
correspond to pennies that all weigh more than 2.9 grams and were
all manufactured before 1983.
d) It appears that something changed around 1983. Possibly the
composition of pennies was changed, so their weights are less
after 1983.

Section 7.3
Statistical Literacy and Critical Thinking

1 A best-fit line (or regression line) is a straight line on a

scatterplot that lies closer to the data points than any other possible
line (according to the standard statistical measure of closeness). A
best-fit line is useful for predicting the value of one of the
variables given some value of the other variable.
2 (1) Don’t expect a best-fit line to give a good prediction unless the
correlation is strong and there are many data points.
(2) Don’t use a best-fit line to make predictions beyond the bounds of
the data points to which the line was fit.
(3) A best-fit line based on past data is not necessarily valid now and
might not result in valid predictions of the future.
(4) Don’t make predictions about a population that is different from
the population from which the sample data were drawn.
(5) A best-fit line is meaningless when there is no significant
correlation or when the relationship is nonlinear.
3 r2 is the square of the correlation coefficient and is called the
coefficient of determination. It tells us the proportion of the
variation that is accounted for by the best-fit line. For example, if r2
=0.9, or 90%, then 90% of the variability is accounted for by the best-
fit line, but 10% is not.
4 Multiple regression is a method for investigating correlation between a
response variable and two or more explanatory variables. It is useful
when more than one explanatory variable may be affecting the same
response variable.
5 This statement makes sense. Assuming the data were collected in a
reasonable way and all ages were sampled, a scatterplot for thousands
of boys should produce a best-fit line that makes reasonable
predictions of mean heights at different ages.
6 This statement does not make sense. When data are tightly clustered
around the best-fit line, the correlation coefficient should be high
(close to 1), and the value of r2 should also be high (close to 1).
7 This statement does not make sense. No one is 12 feet tall (or has a
footprint length of 36 inches), so no data can have been collected for
such sizes, and we cannot assume that the best-fit line for smaller
sizes would apply to such large ones.
8 This statement makes sense. All these factors would be expected to have
an influence on future earnings, so multiple regression analysis would
be useful.

Copyright © 2018 Pearson Education, Inc.

 SECTION 7.3, BEST-FIT LINES AND PREDICTION 93

Concepts and Applications

Note: For Exercise 9-16. Here is one way to add a best-fit line to the scatter
diagram. Enter the Color and Price data from Table 7.1 into an Excel spreadsheet
with Color in the left-hand column. Highlight the two sets of data (including
column headings) and click on the Insert tab icon at the top of the spreadsheet.
Select the Scatter icon option and use the top left sub-type option. The graph
should appear on the spreadsheet. Now right click on any one of the data points
in the graph and click on “Add Trendline.” Select the “Linear” option and click
on “Close.”

Lemon Imports and Car Crashes (U.S.)

16 y = -0.0028x + 16.491
(per 100,000 population)

R² = 0.9196
Crash fatality rate

15.5

15

14.5
200 300 400 500 600
Lemon imports (metric tons)

a) The best-fit line shows a very good fit to the points in

the scatterplot.
b) There is a strong negative correlation; r = ‒0.959 (exact value) and
r2 ≈ 0.920; 92% of the variation in the crash fatality rate can be
accounted for by the linear relationship between lemon imports and the
crash fatality rate, as represented by the best-fit line.
c) None of the points appear to be outliers.
d) The value of r is high and the points appear to be fairly close to the
best-fit line, so the best-fit line appears to provide reasonably
reliable predictions within the range of the given data.
10
College Enrollment and y = 3.467x - 36.767
Enrollment (thousands of

Campus Burglaries R² = 0.3151

200
students)

100

0
25 35 45 55
Burglaries

a) The best-fit line shows a fairly poor fit to the points in

the scatterplot.
b) There is a moderate positive correlation; r = 0.561 (exact value) and
r2 ≈ 0.315; 31.5% of the variation in burglaries can be accounted for
by the linear relationship between enrollment and burglaries, as
represented by the best-fit line.
c) One possible outlier is the point farthest to the right: (53, 86). It
is not extreme enough to have too much of an effect.

Copyright © 2018 Pearson Education, Inc.

94 CHAPTER 7, CORRELATION AND CAUSALITY

d) The value of r is not very high and the points are not very close
to the best-fit line, so the best-fit line does not appear to
provide reasonably reliable predictions within the range of the
given data.
11
80
Altitude and Air Temperature
60
Altitude (thousands of feet)

y = -3.6843x + 72.498
40 R² = 0.9936
20

0
0 5 10 15 20 25 30 35
-20
Temperature (degrees F)
-40

-60
a) The best-fit line shows a very good fit to the points in
the scatterplot.
b) There is a strong negative correlation; r = ‒0.997 (exact value)
and r2 ≈ 0.994; 99.4% of the variation in temperature can be
accounted for by the linear relationship between altitude and
temperature, as represented by the best-fit line.
c) None of the points appear to be outliers.
d) The value of r is high and the points appear to be very close to
the best-fit line, so the best-fit line appears to provide very
reliable predictions within the range of the given data.
12

Post-Care Car Repair Costs

4000 y = -0.1856x + 2062.6
for Full-Rear Crash Tests

R² = 0.0798
3000
Repair Cost (in $)

2000
1000
0
0 2000 4000 6000
Repair Cost (in $) for Full-Front Crash Tests

a) The best-fit line shows a very poor fit to the points in

the scatterplot.
b) There is a very weak negative correlation; r = ‒0.283 (exact
value) and r2 ≈ 0.080; 8% of the variation in rear repair costs
can be accounted for by the linear relationship between front
repair costs and rear repair costs, as represented by the best-
fit line.
c) The point (1032, 3191) is a possible outlier. It is not too
extreme, so it is not likely to have much of an effect.
d) The value of r is low and the points do not appear to be close to
the best-fit line, so the best-fit line does not appear to
provide very reliable predictions within the range of the given
data.
Copyright © 2018 Pearson Education, Inc.
 SECTION 7.3, BEST-FIT LINES AND PREDICTION 95

13
Brain Size and IQ

140 y = -0.0584x + 174.6

R² = 0.2041
IQ Score
120

100

80
950 1050 1150 1250 1350
brain sizes (in cm3)

a) The best-fit line shows a very poor fit to the points in

the scatterplot.
b) There is a very weak positive correlation; r = 0.179 (exact value) and
r2 ≈ 0.032; 3.2% of the variation in IQ scores can be accounted for by
the linear relationship between brain size and IQ score, as
represented by the best-fit line.
c) The point (1285, 102), the farthest to the right, is a possible
outlier. It is not too extreme, so it is not likely to have much of
an effect.
d) The value of r is low and the points do not appear to be close to the
best-fit line, so the best-fit line does not appear to provide very
reliable predictions within the range of the given data.
14

Blood Pressure in
Left Arm Blood Pressure

Left and Right Arms

190
(in mm Hg)

170
150 y = 1.3147x + 43.565
R² = 0.7518
130
70 80 90 100 110
Right Arm Blood Pressure
(in mm Hg)

a) The best-fit line shows a fairly good fit to the points in

the scatterplot.
b) There is a strong positive correlation; r = 0.867 (exact value) and
r2 ≈ 0.752; 75.2% of the variation in the systolic blood pressure in
the right arm can be accounted for by the linear relationship between
the systolic blood pressures in the right and left arms, as
represented by the best-fit line.
c) There is a large gap between the two points at the left and the three
points at the right. With such a small data set, none of the points
are likely to be outliers.
d) The value of r is high and the points appear to be somewhat close to
the best-fit line, so the best-fit line appears to provide somewhat
reliable predictions within the range of the given data.

Copyright © 2018 Pearson Education, Inc.

96 CHAPTER 7, CORRELATION AND CAUSALITY

15

Opening and Winning Auction Bids

800
y = 0.4291x - 4.6218
600
R² = 0.8966
400

200

0
0 500 1000 1500 2000

a) The best-fit line shows a fairly good fit to the points in

the scatterplot.
b) There is a strong positive correlation; r = 0.947 (exact value) and
r2 ≈ 0.897; 89.7% of the variation in the winning bids can be
accounted for by the linear relationship between the opening bids and
the winning bids, as represented by the best-fit line.
c) The point (1500, 650) in the upper-right corner is an outlier. That
point has a very strong effect on the results. Deleting that outlier
changes r from 0.947 to 0.000.
d) Given that the outlier has such a strong effect on the results, the
best-fit line does not appear to provide very reliable predictions
within the range of the given data.
16

Ages of Academy Award Winners

(Selected Years)
80 y = -0.1174x + 48.076
Ages (in years) of Male

R² = 0.0296
60
40
Actors

20
20 30 40 50 60 70
Ages (in years) of Female Actresses

a) The best-fit line shows a very poor fit to the points in

the scatterplot.
b) There is a very weak negative correlation; r = ‒0.172 (exact value)
and r2 ≈ 0.030; 3% of the variation in ages of female and male actors
can be accounted for by the linear relationship between those ages,
as represented by the best-fit line.
c) None of the points appear to be outliers.
d) The value of r is low and the points do not appear to be close to the
best-fit line, so the best-fit line does not appear to provide very
reliable predictions within the range of the given data.

Copyright © 2018 Pearson Education, Inc.

 SECTION 7.4, THE SEARCH FOR CASAULITY 97

Section 7.4
Statistical Literacy and Critical Thinking

1 Finding a correlation involves finding a statistical association or

relationship, and there may or may not be causality between the two
variables. Establishing causality between two variables means that finding
that one of the variables has a direct effect on the other variable.
2 Researchers began to suspect causality because they found correlations
between smoking and lung cancer. More smoking was correlated with higher
rates of lung cancer. They compared results with nonsmokers and accounted for
other potential causes, and the correlations persisted. They then conducted
controlled experiments with animals, and ultimately discovered the
biochemical processes through which smoking leads to cancer-causing
mutations.
3 1. Look for situations in which the effect is correlated with the suspected
cause even while other factors vary.
2. Among groups that differ only in the presence or absence of the suspected
cause, check that the effect is similarly present or absent.
3. Look for evidence that larger amounts of the suspected cause produce
larger (or smaller) amounts of the effect.
4. If the effect might be produced by other potential causes (besides your
suspected cause), make sure that the effect still remains after accounting
for these other potential causes.
5. If possible, test the suspected cause with an experiment. If the
experiment cannot be performed with humans for ethical reasons, consider
doing the experiment with animals, cell cultures, or computer models.
6. Try to determine the physical mechanism by which the suspected cause
produces the effect.
4 Possible cause, probable cause, and cause beyond reasonable doubt. While
these broad categories come from the legal system, they are useful when
considering how well we have established causality using statistics.
5 The statement makes sense. Researchers cannot randomly assign people to
treatment and control groups and ask subjects in the treatment group to
smoke.
6 This statement does not make sense. Even a “perfect” correlation coefficient
of r = 1 may occur due to coincidence or a common underlying cause.
7 The statement makes sense. The correlation suggested further investigations,
which supported causality.
8 This statement does not make sense. “Reasonable doubt” is not the same as
“all doubt,” and there is always a chance that a conclusion is incorrect even
though it has been established beyond reasonable doubt.

Concepts and Applications

9 The causal connection is valid. When athletes train more for a marathon, they
tend to do better in the sense of achieving a lower time to complete the
marathon.
10 The causal connection is not valid, but many people spend large amounts of
money based on an incorrect belief that exposure to a magnet will result in
reduced pain.
11 This causal connection is valid. Alcohol is a depressant to the central
nervous system, and it has several effects that include decreased reaction
time. This is one important reason why drinking and driving is so dangerous.
12 The causal connection is not valid but there may be people that use
meditation in higher paying/stress jobs to lower their stress levels.

Copyright © 2018 Pearson Education, Inc.

98 CHAPTER 7, CORRELATION AND CAUSALITY

13 Higher altitudes are associated with lower amounts of oxygen, and the
reductions in oxygen affect different people in different ways.
Experienced and well-trained climbers are less likely to develop
headaches or disorientation.
14 Susceptibility involves other factors than just smoking and varies among
individuals. Also, some smokers die of other causes first.
15 Smoking can only increase a risk that is already present.
16 The study compared the life expectancy of conductors with that of all
American males including those who die as infants and children.
Conductors don’t usually become conductors until they are middle aged,
say at least 30 years old. So they are not a representative sample of
the population (they are older on the average) and should be expected to
have a higher average life span than that of all males.
17 This was an observational study. Later child bearing reflects an
underlying cause. While it’s possible that the conclusions are correct,
there are other possible explanations for the findings. For example,
it’s also possible that the younger women lived during a time when
having babies after age forty was less likely (by choice). It is still
possible for them to live to be 100.
18 The people who live near the high voltage lines may all be exposed to
some other common cause of cancer in the same area; for example, radium
in the soil or pollutants in the water sources or air. Any experiment
to isolate the cause (for example, removing the high voltage power
lines) will require many years to be conclusive.
19 Availability is not itself a cause. Social, economic, or personal
conditions may also cause individuals to use the available weapons.
20 The vasectomies do not cause prostate cancer; it’s the visits to the
doctor that increase the chance of detecting cancer.

Chapter 7 Review Exercises

1 The scatterplot suggests that there is a strong positive correlation

between the cost of a slice of pizza and the subway fare.
New York City Pizza
and Subway Costs
Subway Fare (in $)

3 y = 1.0109x - 0.0111
2 R² = 0.9836

1
0
0 1 2 3
Pizza Cost (in $)

2 The correlation coefficient is r = 0.992, which suggests that there is a

strong positive correlation between the cost of a slice of pizza and the
subway fare.
3 No, we cannot conclude that the cost of a slice of pizza has a direct
causal effect on the subway fare. Correlation does not imply causality.
It is likely that other variables have a direct influence on pizza cost
and subway fare.
4 r2 = 0.984. That value tells us that 98.4% of the variation in subway
fares can be explained as the linear relationship between pizza cost and
subway fare, as represented by the best-fit line.

Copyright © 2018 Pearson Education, Inc.

 CHAPTER 7 QUIZ 99

5 Yes, the best-fit line can be used to make a reasonably good prediction of
subway fare given the cost of a slice of pizza. Since r is so high and
because the points on the scatterplot are quite close to the best-fit line,
the predictions should be reasonably accurate, assuming that they don’t go
too far beyond the range of the given data and that conditions do not change
dramatically.
6 The predicted subway fare is not necessarily an accurate prediction. The cost
of $1000 for a slice of pizza is substantially far beyond the range of the
given data, so predictions might not be very accurate.
7 The points on the scatterplot lie on a straight line with negative slope.
(The negative slope indicates that the line falls from left
to right.)
8 Correlation alone never implies causation, and, in this case, certainly more
trips to the dentist do not cause higher incomes. Households with more
disposable income can afford more trips to the dentist or can afford dental
insurance that covers the costs of those trips.
9 It’s possible that the variables represented by the data values are related
in some nonlinear way. For example, the scatterplot might show a curved
pattern instead of a straight line.
10 The scatterplot appears to show a strong negative correlation. The exact
value of the correlation coefficient is r = ‒0.967.

Chapter 7 Quiz

1 Every possible correlation coefficient must lie between the values of

–1 and 1.
2 The variables in a, d, and e are likely to be correlated, while those in b
and c are not likely to be correlated.
3 Only statement c can be used to describe the relationship between the two
variables. Statement d is not valid regardless of the strength of the
correlation. Statement e is not valid since it is possible, but not ensured,
that one of the variables is the direct cause of the other variable.
4 There is a strong negative correlation between x and y in the diagram,
probably in the neighborhood of –0.9. (The actual value of r is –0.934.)
5 Yes. The data points all lie close to a straight line.
6 If r = 0.900, then 90% of the variation in the response variable y can be
explained by the linear relationship between x and y as described by the
best-fit line.
7 False. r2 is the proportion of the variation in a variable that is accounted
for by the best-fit line.
8 True. If r = 1 or r = -1 then the correlation is 100% positive (r = 1) or
100% negative (r = -1). All points from the scatterplot would be on the best
fit line.
9 False. There may be no pattern, or a pattern indicating some kind of
relationship between two variables.
10 False. The line of best fit could pass through no points, some points, or
all of the points. Only when there are only two points is the best fit line
guaranteed to pass through all the points.

Copyright © 2018 Pearson Education, Inc.