Statistics Unlocking the Power of Data 1st Edition Lock Test Bankpdf download
Statistics Unlocking the Power of Data 1st Edition Lock Test Bankpdf download
https://testbankfan.com/product/statistics-unlocking-the-power-
of-data-1st-edition-lock-test-bank/
We believe these products will be a great fit for you. Click
the link to download now, or visit testbankfan.com
to discover even more!
https://testbankfan.com/product/statistics-unlocking-the-power-
of-data-1st-edition-lock-solutions-manual/
https://testbankfan.com/product/introductory-statistics-
exploring-the-world-through-data-1st-edition-gould-test-bank/
https://testbankfan.com/product/introductory-statistics-
exploring-the-world-through-data-1st-edition-gould-solutions-
manual/
https://testbankfan.com/product/management-of-human-resources-
the-essentials-canadian-5th-edition-dessler-test-bank/
Research Methods and Statistics for Public and
Nonprofit Administrators 1st Edition Nishishiba Test
Bank
https://testbankfan.com/product/research-methods-and-statistics-
for-public-and-nonprofit-administrators-1st-edition-nishishiba-
test-bank/
https://testbankfan.com/product/real-estate-principles-a-value-
approach-5th-edition-ling-test-bank/
https://testbankfan.com/product/memory-foundations-and-
applications-3rd-edition-schwartz-test-bank/
https://testbankfan.com/product/taxation-of-individuals-5th-
edition-spilker-solutions-manual/
https://testbankfan.com/product/algebra-and-trigonometry-6th-
edition-blitzer-solutions-manual/
Practical Research Planning and Design 11th Edition
Leedy Test Bank
https://testbankfan.com/product/practical-research-planning-and-
design-11th-edition-leedy-test-bank/
1. Use the following to answer questions a-c:
Consider taking samples of size 100 from a population with proportion 0.33.
c. Is the sample size large enough for the Central Limit Theorem to apply so that the sample
proportions follow a normal distribution?
A) Yes B) No
Ans: A Difficulty: Medium L.O.: 6.1.2
c. Is the sample size large enough for the Central Limit Theorem to apply so that the sample
proportions follow a normal distribution?
A) Yes B) No
Ans: B Difficulty: Medium L.O.: 6.1.2
Suppose that the makers of M&M's claim that 24% of their Milk Chocolate M&M's are blue.
3. Assume that Fun-Size bags of Milk Chocolate M&M's hold 20 candies. Find the mean
and standard error of the distribution of sample proportions of blue candies for Fun-Size
bags (i.e., samples of size 20). Use four decimal places when reporting the standard error.
Ans: mean = 0.24
0.24*0.76
standard error = = 0.0955
20
Difficulty: Medium L.O.: 6.1.1
Page 1
Chapter 6: Inference for Means and Proportions
4. Assume that the bags of Milk Chocolate M&M's sold in vending machines have 55
candies. Find the mean and standard error of the distribution of sample proportions of
blue candies for vending machine bags (i.e., samples of size 55). Use four decimal
places when reporting the standard error.
Ans: mean = 0.24
0.24*0.76
standard error = = 0.0576
55
Difficulty: Medium L.O.: 6.1.1
5. Assume that bags of Milk Chocolate M&M's labeled as "Medium" size contain 415
candies. Find the mean and standard error of the distribution of sample proportions of
blue candies for Medium bags (i.e., samples of size 415). Use four decimal places when
reporting the standard error.
Ans: mean = 0.24
0.24*.76
standard error = = 0.0210
415
Difficulty: Medium L.O.: 6.1.1
6. Would you expect using bags of Milk Chocolate M&M's labeled as "Large" size, which
contain more candies than the "Medium" size bags, to result in a larger or smaller
standard error?
A) Larger B) Smaller
Ans: B Difficulty: Medium L.O.: 6.1.1
7. For which sample sizes (Fun-Size with 20, Vending Machine with 55, or Medium with
415) would the Central Limit Theorem apply?
Ans: The Central Limit Theorem would apply for the Vending Machine and Medium
size bags (but not the Fun-Size).
8. Suppose you purchase a bag of Milk Chocolate M&M's from a vending machine and
only 8 of your 55 candies are blue. Assuming that the sample proportions are normally
distributed, what percent of vending machine bags (i.e., samples of size 55) will have a
sample proportion smaller than 0.145? Use two decimal places when reporting your
answer.
Ans: 0.05 (found using Statkey)
Difficulty: Medium L.O.: 5.1.0; 6.1.0
Page 2
Chapter 6: Inference for Means and Proportions
Admissions records at a small university indicates that 6.7% of the students enrolled are
international students.
9. Find the mean and standard error of the sample proportion of international students in
random samples of size 50. Use four decimal places when reporting the standard error.
Ans: mean = 0.067
0.067*0.933
standard error = = 0.0354
50
Difficulty: Medium L.O.: 6.1.1
10. Find the mean and standard error of the sample proportion of international students in
random samples of size 100. Use four decimal places when reporting the standard error.
Ans: mean = 0.067
0.067*0.933
standard error = = 0.0250
100
Difficulty: Medium L.O.: 6.1.1
11. Find the mean and standard error of the sample proportion of international students in
random samples of size 200. Use four decimal places when reporting the standard error.
Ans: mean = 0.067
0.067*0.933
standard error = = 0.0177
200
Difficulty: Medium L.O.: 6.1.1
12. For which sample sizes (n = 50, n = 100, and n = 200) would the Central Limit Theorem
apply?
Ans: Only the sample of size n = 200.
13. What proportion of samples of 200 randomly selected students will have at least 8%
international students? Use three decimal places when reporting your answer.
Ans: 0.231 (found using Statkey)
Difficulty: Medium L.O.: 5.1.0; 6.1.0
Page 3
Chapter 6: Inference for Means and Proportions
A 2009 study to investigate the dominant paws in cats was described in Animal Behaviour
(Volume 78, Issue 2). The researchers used a random sample of 42 domestic cats. In this study,
each cat was shown a treat (5 grams of tuna), and while the cat watched, the food was placed
inside a jar. The opening of the jar was small enough that the cat could not stick its head inside to
remove the treat. The researcher recorded the paw that was first used by the cat to try to retrieve
the treat. This was repeated 100 times for each cat (over a span of several days). The paw used
most often was deemed the dominant paw (note that one cat used both paws equally and was
classified as "ambidextrous"). Of the 42 cats studied, 20 were classified as "left-pawed".
14. Verify that the sample is large enough to use the normal formula to find a confidence
interval for the proportion of domestic cats that are "left-pawed".
Ans: p̂ = 20/42 = 0.476
npˆ = 20 > 10, n(1 − pˆ ) = 22 > 10 <-- Yes, we can use the normal formula
Difficulty: Medium L.O.: 6.2.0
15. Construct a 95% confidence interval for the proportion of domestic cats that are
"left-pawed". Use three decimal places in your margin of error.
Ans: p̂ = 20/42 = 0.476
(0.476)(1 − 0.476)
0.476 1.96
42
0.476 0.151
0.325 to 0.627
Difficulty: Medium L.O.: 6.2.1
16. Provide an interpretation of your interval in the context of this data situation.
Ans: We are 95% sure that the proportion of domestic cats that are "left-pawed" is
between 0.325 and 0.627.
Difficulty: Medium L.O.: 3.2.4; 6.2.0
17. Another researcher wants to conduct a similar study to more precisely estimate the
proportion of cats that are "left-pawed". They want to construct a 95% confidence
interval that has a margin of error of 6%. How many cats does she need to use in her
sample?
Ans: Use the results of the original study as p = 0.476.
2
1.96
n= (0.476)(1 − 0.476) = 266.2
0.06
She needs 267 cats to meet her goal.
Difficulty: Medium L.O.: 6.2.2
Page 4
Chapter 6: Inference for Means and Proportions
In an October 2012 survey of 7,786 randomly selected adults living in Germany, 5,840 said they
exercised for at least 30 minutes three or more times per week.
18. Verify that the sample is large enough to use the normal formula to find a confidence
interval for the proportion of Germans who exercises for 30 minutes three or more times
a week.
Ans: p̂ = 5,840/7,786 = 0.75
npˆ = 5,840 > 10, n(1 − pˆ ) = 1,946 > 10 <-- yes, we can use the normal formula
Difficulty: Medium L.O.: 6.2.0
19. Construct a 99% confidence interval for the proportion of Germans who exercise for 30
minutes three or more times a week. Use three decimal places in your margin of error.
Ans: p̂ = 5,840/7,786 = 0.75
0.75*0.25
0.75 2.575
7, 786
0.75 0.013
0.737 to 0.763
Difficulty: Medium L.O.: 6.2.1
20. Provide an interpretation of your interval in the context of this data situation.
Ans: We are 99% sure that the proportion of Germans who exercise for 30 minutes three
or more times a week is between 0.737 and 0.763.
Difficulty: Medium L.O.: 3.2.4; 6.2.0
21. Suppose an exercise scientist wants to estimate the proportion of American adults who
exercise for 30 minutes three or more times per week. He wants to construct a 90%
confidence interval with a margin of error of 1%. Note that Americans are typically
thought to not be as active as individuals in other countries, and thus the estimate from
Germany is likely not a good estimate for Americans. What sample size does he need?
Ans: Use p = 0.5 because 75% is not a good estimate for Americans and we don't have
a better guess.
2
1.645
n= *0.5*0.5 = 6,765.1
0.01
Page 5
Chapter 6: Inference for Means and Proportions
In an August 2012 Gallup survey of 1,012 randomly selected U.S. adults (age 18 and over), 53%
said that they were dissatisfied with the quality of education students receive in kindergarten
through grade 12.
22. Verify that the sample is large enough to use the normal formula to find a confidence
interval for the proportion of Americans who are dissatisfied with the quality of
education students receive in kindergarten through grade 12.
Ans: p̂ = 0.53
npˆ = 536.36 > 10, n(1 − pˆ ) = 475.64 > 10 <-- Yes, we can use the normal formula
Difficulty: Medium L.O.: 6.2.0
23. Construct a 90% confidence interval for the proportion of U.S. adults who are dissatisfied
with the quality of education students receive in kindergarten through grade 12. Use three
decimal places in your margin of error.
0.53*0.47
Ans: 0.53 1.645
1, 012
0.53 0.026
0.504 to 0.556
Difficulty: Medium L.O.: 6.2.1
24. Provide an interpretation of your interval in the context of this data situation.
Ans: We are 90% sure that the proportion of U.S. adults who are dissatisfied with the
quality of education students receive in kindergarten through grade 12 is between
0.504 and 0.556.
Difficulty: Medium L.O.: 2.3.4; 6.2.0
25. Suppose you want to estimate the proportion of local adults who are dissatisfied with the
education students receive in kindergarten through grade 12 with 95% confidence and a
5% margin of error. If you suspect that local adults won't differ drastically from those
Gallup used, how many people should you sample?
Ans: Use p = 0.53 (because we don't suspect the local adults to drastically differ from
the Gallup sample)
2
1.96
n= (0.53)(0.47) = 382.8
0.05
Page 6
Chapter 6: Inference for Means and Proportions
26. Test, at the 5% level, if this sample provides evidence that the proportion of Americans
who are dissatisfied with education in kindergarten through grade 12 differs significantly
from 50%. Be sure to verify that it is appropriate to use a normal distribution to compute
the p-value and include all of the details of the test.
Ans: p = proportion of U.S. adults who are dissatisfied with education in kindergarten
through grade 12.
Ho: p = 0.50
Ha: p 0.50
Since both are larger than 10, the sample size is large enough to use the normal
distribution to compute the p-value.
0.53 − 0.50
Test statistic: z = = 1.909
0.5*0.5
1, 012
Since the p-value is larger than the 5% significance level, there is no evidence to
reject Ho and thus there is no evidence to conclude that proportion of U.S. adults
who are dissatisfied with education in kindergarten through grade 12 differs
significantly from 50%.
Difficulty: Medium L.O.: 6.3.1
A sample of 148 college students at a large university reports getting an average of 6.85 hours of
sleep last night with a standard deviation of 2.12 hours.
27. Verify that it is reasonable to use the t-distribution to construct a confidence interval for
the average amount of sleep students at this university got last night.
Ans: A sample of size 148 is large enough to use the Central Limit Theorem.
Difficulty: Medium L.O.: 6.4.2
Page 7
Chapter 6: Inference for Means and Proportions
28. Construct a 98% confidence interval for the average amount of sleep students at this
university got last night. Use two decimal places in your margin of error.
Ans: n = 148 df = 147 t* = 2.352 (using Statkey)
2.12
6.85 2.352
148
6.85 0.41
6.44 to 7.26 hours
Difficulty: Medium L.O.: 6.4.3; 6.5.1
29. Provide an interpretation of your interval in the context of this data situation.
Ans: We are 98% sure that the mean amount of sleep students at this university got last
night is between 6.44 and 7.26 hours.
Difficulty: Medium L.O.: 3.2.4; 6.5.0
30. Suppose you want to conduct a similar study at your university. Assuming that the
standard deviation of this sample is a reasonable estimate of the standard deviation of
sleep time at your university, how many students do you need to survey to estimate the
mean sleep time of students at your university with 95% confidence and a margin of error
of 0.5 hours?
Ans: = 2.12
2
1.96* 2.12
n= =69.1
0.5
Page 8
Chapter 6: Inference for Means and Proportions
An Internet provider contacts a random sample of 300 customers and asks how many hours per
week the customers use the Internet. The responses are summarized in the provided dotplot. The
average amount of time spent on the Internet per week was 7.2 hours, with a standard deviation
of 7.9 hours.
31. Is it reasonable to use the t-distribution to construct a confidence interval for the average
amount of time customers of this Internet provider spend on the Internet each week?
Explain briefly.
Ans: Yes, even though the distribution is skewed with some outliers, the sample size is
extremely large (n = 300).
Difficulty: Medium L.O.: 6.4.2
32. Construct a 95% confidence interval for the average amount of time customers of this
Internet provider spend on the Internet each week. Round the margin of error to one
decimal place.
Ans: n = 300 df = 299 t* = 1.968
7.9
7.2 1.968
300
7.2 0.9
6.3 to 8.1 hours
Difficulty: Medium L.O.: 6.4.3; 6.5.1
Page 9
Chapter 6: Inference for Means and Proportions
33. Provide an interpretation of your interval in the context of this data situation.
Ans: We are 95% sure that the average amount of time customers of this Internet
provider spend on the Internet each week is between 6.3 and 8.1 hours.
Difficulty: Medium L.O.: 3.2.4; 6.5.0
34. If we want a margin of error of 0.5 hours, how large of a sample would we need?
2
1.96*7.9
Ans: n = = 959.02
0.5
According to the National Science Foundation, individuals who graduated in 2010 with a
doctoral degree had an average of $14,115 graduate debt. Assume that the standard deviation of
graduate debt is $26,400. If we take lots of samples of individuals who graduated in 2010 with a
doctoral degree, what would you expect the mean and standard error of the distribution of
sample mean graduate debt amounts to be in each case? In each case, use two decimal places
when reporting your standard error.
a. n = 200 individuals
Ans: mean: =$14,115
26, 400
SE = = $1,866.76
200
Difficulty: Medium L.O.: 6.4.1
b. n = 500 individuals
Ans: mean: =$14,115
26, 400
SE = = $1,180.64
500
Difficulty: Medium L.O.: 6.4.1
For each of the following, assume that the sample is a random sample from a distribution that is
reasonably normally distributed and that we are doing inference for a population mean.
a. Find endpoints of a t-distribution with 2.5% beyond them in each tail if the sample has
size n = 15.
Ans: -2.145 and 2.145
Difficulty: Easy L.O.: 6.4.3
Page 10
Chapter 6: Inference for Means and Proportions
b. Find endpoints of a t-distribution with 10% beyond them in each tail if the sample has
size n = 5.
Ans: -1.533 and 1.533
Difficulty: Easy L.O.: 6.4.3
c. Find endpoints of a t-distribution with 3% beyond them in each tail if the sample has size
n = 60.
Ans: -1.918 and 1.918
Difficulty: Medium L.O.: 6.4.3
d. Find endpoints of a t-distribution with 1.5% beyond them in each tail if the sample has
size 22.
Ans: -2.328 and 2.328
Difficulty: Easy L.O.: 6.4.3
e. Find the area in a t-distribution to the right of 2.6 if the sample has size n = 16.
Ans: 0.01
Difficulty: Easy L.O.: 6.4.3
f. Find the area in a t-distribution to the right of 1.75 if the sample has size n = 4.
Ans: 0.089
Difficulty: Medium L.O.: 6.4.3
g. Find the area in a t-distribution to the left of -2.7 if the sample has size n = 35.
Ans: 0.0054
Difficulty: Medium L.O.: 6.4.3
h. Find the area in a t-distribution to the left of -0.68 if the sample has size n = 20.
Ans: 0.252
Difficulty: Medium L.O.: 6.4.3
For each of the following, find the mean and standard error of the distribution of sample means.
Use two decimal places when reporting your standard error.
37. Samples of size 15 from a population with mean 25 and standard deviation 4.
Ans: mean: = 25
4
SE = = 1.03
15
Difficulty: Medium L.O.: 6.4.1
Page 11
Chapter 6: Inference for Means and Proportions
38. Samples of size 50 from a population with mean 450 and standard deviation 75.
Ans: mean: = 450
75
SE = = 10.61
50
Difficulty: Medium L.O.: 6.4.1
39. Samples of size 25 from a population with mean 10 and standard deviation 2.
Ans: mean: = 10
2
SE = = 0.40
25
Difficulty: Medium L.O.: 6.4.1
40. Samples of size 250 from a population with mean 80 and standard deviation of 15.
Ans: mean: = 80
15
SE = = 0.95
250
Difficulty: Medium L.O.: 6.4.1
A dotplot and the summary statistics for a sample are provided. In each case, indicate whether or
not it is appropriate to use the t-distribution.
Page 12
Chapter 6: Inference for Means and Proportions
Page 13
Chapter 6: Inference for Means and Proportions
November 6, 2012 was election day. Many of the major television networks aired coverage of
the incoming election results during the primetime hours. The provided boxplot displays the
amount of time (in minutes) spent watching election coverage for a random sample of 25 U.S.
adults. In this sample, the average time spent watching election coverage was 80.44 minutes with
standard deviation of 43.99 minutes.
45. Is it reasonable to use the t-distribution to construct a confidence interval for the average
amount of time spent watching election coverage by U.S. adults? Explain briefly.
Ans: Yes. We have a moderate sample size (n = 25) and there are no outliers or extreme
skewness in the boxplot.
Difficulty: Medium L.O.: 6.4.2
46. Construct a 90% confidence interval for the average amount of time U.S. adults spent
watching election coverage. Use two decimal places in your margin of error.
43.99
Ans: 80.44 1.711
25
80.44 15.05
47. Provide an interpretation of your interval in the context of this data situation.
Ans: We are 90% sure that the average amount of time spent watching election coverage
by U.S. adults is between 65.39 and 95.49 hours.
Difficulty: Medium L.O.: 3.2.4; 6.5.0
Page 14
Chapter 6: Inference for Means and Proportions
48. What sample size would we need to estimate the average amount of time U.S. adults
watching election coverage with 99% confidence and a margin of error of 5 hours?
2
2.575* 43.99
Ans: n = = 513.24
5
Turkey is a staple at most traditional Thanksgiving dinners. A random sample of 12 grocery store
customers were asked about the size of the turkey they were purchasing for Thanksgiving. The
average weight was 13.9 pounds with a standard deviation of 2.2 pounds. The boxplot displays
the distribution of the sample turkey weights.
49. Is is reasonable to use the t-distribution to construct a confidence interval for the average
weight of turkeys purchased at this store? Explain briefly.
Ans: Yes, even though we have a small sample size, the boxplot is fairly symmetric and
there are no outliers.
Difficulty: Medium L.O.: 6.4.2
Page 15
Chapter 6: Inference for Means and Proportions
50. Construct a 99% confidence interval for the average weight of turkeys purchased at this
store. Round your margin of error to two decimal places.
2.2
Ans: 13.9 3.105
12
13.9 1.97
51. Provide an interpretation of your interval in the context of this data situation.
Ans: We are 99% sure that the mean weight of turkeys purchased at this store is between
11.93 and 15.87 pounds.
Difficulty: Medium L.O.: 3.2.4; 6.5.0
52. What sample size would we need to reduce the margin of error to 1 pound?
2
2.575* 2.2
Ans: n = =32.09
1
53. According to the Minnesota Turkey Growers Association's website, the average weight
of turkeys purchased for Thanksgiving dinner is 15 pounds. Test, at the 5% level, if this
sample provides evidence that the average weight of turkeys purchased at this store
differs from 15 pounds. Include all of the details of the test.
Ans: = mean weight of turkeys purchased at this store
Ho: = 15
Ho: 15
13.9 − 15
Test Statistic: t = = -1.732
2.2
12
The sample data look roughly symmetric with no outliers, so we can use the
t-distribution with 11 degrees of freedom to compute the p-value.
p-value = 0.111
Because the p-value is larger than the 5% significance level, we have no evidence
to reject Ho and thus have no evidence to conclude that the average weight of
turkeys purchased at this store differs significantly from the 15 pounds reported by
the Minnesota Turkey Growers Association.
Difficulty: Medium L.O.: 6.6.1
Page 16
Chapter 6: Inference for Means and Proportions
A study published in 2008 in the American Journal of Health Promotion (Volume 22, Issue 6)
by researchers at the University of Minnesota (U of M) found that 124 out of 1,923 U of M
females had over $6,000 in credit card debt while 61 out of 1,236 males had over $6,000 in
credit card debt.
54. Verify that the sample size is large enough in each group to use the normal distribution to
construct a confidence interval for a difference in two proportions.
Ans: n f pˆ f = 124 > 10
n f (1 − pˆ f ) = 1,799 > 10
nm pˆ m = 61 > 10
nm (1 − pˆ m ) = 1,175 > 10
Since all are greater than 10, the sample size is large enough in each group to use
the normal distribution to construct the confidence interval.
Difficulty: Medium L.O.: 6.8.0
55. Construct a 95% confidence interval for the difference between the proportions of female
and male University of Minnesota students who have more than $6,000 in credit card
debt (pf - pm). Round your sample proportions and margin of error to four decimal places.
Ans: pˆ f − pˆ m = 124/1,923 - 61/1,236 = 0.0645 - 0.0494 = 0.0151
Page 17
Chapter 6: Inference for Means and Proportions
56. Test, at the 5% level, if there is evidence that the proportion of female students at U of M
with more that $6,000 credit card debt is greater than the proportion of males at U of M
with more than $6,000 credit card debt. Include all details of the test.
Ans: Ho: pf = pm
Ha: pf > pm
pf = proportion of female U of M students with more than $6,000 credit card debt
pm = proportion of male U of M students with more than $6,000 credit card debt
61 + 124 185
Pooled proportion (for standard error): pˆ = = = 0.0586
1, 236 + 1,923 3,159
0.0645 − 0.0494
Test statistic: z = = 1.763
1 1
0.0586(1 − 0.0586) +
1, 236 1,923
We can use the normal distribution to compute the p-value because both samples
have at least 10 successes and failures.
Because the p-value is less than the 5% significance level, we have evidence to
reject the null hypothesis and conclude that the proportion of female U of M
students with more than $6,000 in credit card debt is significantly higher than the
proportion of male U of M students with more than $6,000 in credit card debt.
Difficulty: Medium L.O.: 6.9.1
Every year since the 1957-58 academic year, the National Science Foundation (NSF) conducts
its Survey of Earned Doctorates (SED) of all individuals receiving research doctoral degrees
from accredited U.S. institutions. The results from the 2010 survey published on the NSF
website indicate that 78.2% of individuals earning their doctorate in the physical sciences have
no graduate debt while 48.3% of those earning their doctorate in the social sciences have no
graduate debt. Of the 48,069 research doctorates granted in 2010, 93% completed the SED, thus
the information collected by the NSF can be good approximations of the population parameters.
Page 18
Chapter 6: Inference for Means and Proportions
a. Suppose we take random samples of 100 individuals who earned a doctorate in the
physical sciences (in 2010) and 100 individuals who earned a doctorate in the social
sciences (in 2010). Find the mean and standard error (using four decimal places) of the
distribution of differences in sample proportions ( pˆ P − pˆ S ), and indicate if the sample
sizes are large enough to use the Central Limit Theorem.
Ans: mean = 0.782 - 0.483 = 0.299
Since all are greater than 10, the sample sizes are large enough to use the Central
Limit Theorem.
Difficulty: Medium L.O.: 6.7.2; 6.7.3
Since nP(1-pP) is not greater than 10, the sample sizes are NOT large enough to
use the Central Limit Theorem.
Difficulty: Medium L.O.: 6.7.2; 6.7.3
Page 19
Chapter 6: Inference for Means and Proportions
Since all are greater than 10, the sample sizes are large enough to use the Central
Limit Theorem.
Difficulty: Medium L.O.: 6.7.2; 6.7.3
Situations comparing two proportions are described. In each case, determine whether the
situation involves comparing proportions for two groups or comparing two proportions from the
same group.
a. Compare the proportion of U.S. adults who have a positive opinion about the media and
the proportion of U.S. adults who have a negative opinion about the media.
A) Comparing proportions for two groups
B) Comparing two proportions from the same group
Ans: B Difficulty: Medium L.O.: 6.7.1
b. Comparing proportion of milk chocolate M&M's that are blue to the proportion of milk
chocolate M&M's that are green.
A) Comparing proportions for two groups
B) Comparing two proportions from the same group
Ans: B Difficulty: Medium L.O.: 6.7.1
c. Comparing the proportion of milk chocolate M&M's that are blue to the proportion of
dark chocolate M&M's that are blue.
A) Comparing proportions for two groups
B) Comparing two proportions from the same group
Ans: A Difficulty: Medium L.O.: 6.7.1
Page 20
Chapter 6: Inference for Means and Proportions
d. Compare the proportion of female students at a university who play a sport to the
proportion of male students at a university who play a sport.
A) Comparing proportions for two groups
B) Comparing two proportions from the same group
Ans: A Difficulty: Medium L.O.: 6.7.1
Students in a small statistics class were asked to count the number of scars both on their
"dominant" hand (the one they use most often) and on their "off" hand. The summary statistics
are provided. It is of interest to compare the average number of scars on the dominant and off
hands.
n x s
Dominant 25 1.92 2.326
Off 25 2.72 3.007
Difference (D - O) 25 -0.8 2.363
59. Why is it appropriate to use paired data in this analysis? Explain briefly.
Ans: Paired data difference in means would be more appropriate here because each
student counts the number of scars on both their dominant and their off hand. Since
there are two measurements on each student, this is paired data.
Difficulty: Medium L.O.: 6.13.1
Page 21
Chapter 6: Inference for Means and Proportions
60. Boxplots of the raw data are provided. Would it be appropriate to use a t-distribution to
construct a confidence interval for, or perform a test about, the difference in the mean
number of scars on dominant and off hands? Specifically mention which boxplot(s) you
are using to justify your answer.
Ans: Since this is a paired data problem, we need to look at the boxplot of the
differences. Since the differences look reasonably symmetric, it is appropriate to
construct a confidence interval for, or perform a test about, the difference in the
mean number of scars on dominant and off hands.
Difficulty: Medium L.O.: 6.13.0; 6.13.3; 6.13.4
61. Construct a 90% confidence interval for the difference in mean number of scars on
dominant and off hands. Round your margin of error to two decimal places.
Ans: n = 25, so df = 24.
The t endpoint for a 90% confidence interval when there are 24 degrees of freedom
is t = 1.711 (found using Statkey).
2.363
-0.8 1.711
25
-0.8 0.81
-1.61 to 0.01
Difficulty: Medium L.O.: 6.13.3
Page 22
Chapter 6: Inference for Means and Proportions
62. Test to see if the mean number of scars on dominant hands is significantly different from
the mean number of scars on off hands. Use a 10% significance level. Include all of the
details of the test.
Ans: d = difference in mean number of scars on dominant and off hands (dominant -
off) (Note D − O = mean number of scars on dominant hand - mean number of
scars on off hand would also be acceptable.)
Ho: d = 0
Ha: d 0
−0.8 − 0
Test statistic: t = = -1.693
2.363
25
n = 25, so df = 24
Since the p-value is larger than the 10% significance level, we have no evidence to
reject Ho and thus have no evidence conclude that there is a significant difference
in the mean number of scars on dominant and off hands.
Difficulty: Medium L.O.: 6.13.4
Page 23
Chapter 6: Inference for Means and Proportions
63. A 2009 study to investigate the dominant paws in cats was described in Animal
Behaviour (Volume 78, Issue 2). The researchers used a random sample of 42 domestic
cats. In this study, each cat was shown a treat (5 grams of tuna), and while the cat
watched, the food was placed inside a jar. The opening of the jar was small enough that
the cat could not stick its head inside to remove the treat. The researcher recorded the
paw that was first used by the cat to try to retrieve the treat. This was repeated 100 times
for each cat (over a span of several days). The paw used most often was deemed the
dominant paw (note that one cat used both paws equally and was classified as
"ambidextrous"). The researchers were also interested in comparing the proportion of
"left-pawed" cats for male and female cats. Of the 21 male cats in the sample, 19 were
classified as "left-pawed" while only 1 of the 21 female cats were considered to be
"left-pawed". Explain why it would not be appropriate to use the normal distribution to
construct a confidence interval for the difference in the proportion of male and female
cats that are "left-pawed".
Ans: nM pˆ M = 19 > 10
nM (1 − pˆ M ) = 2 < 10 X
nF pˆ F = 20 > 10
nF (1 − pˆ F ) = 1 < 10 X
Since there are only two "failures" in the sample of male cats and only 1 "failure"
in the sample of female cats, the sample sizes are not large enough to use the
Central Limit Theorem.
Difficulty: Medium L.O.: 6.8.1
February 12, 2009 marked the 200th anniversary of Charles Darwin's birth. To celebrate, Gallup,
a national polling organization, surveyed 1,018 randomly selected American adults about their
education level and their beliefs about the theory of evolution. In their sample, 325 of their
respondents had some college education and 228 were college graduates. Among the 325
respondents with some college education, 133 said that they believed in the theory of evolution.
Among the 228 respondents who were college graduates, 121 said that they believed in the
theory of evolution.
Page 24
Chapter 6: Inference for Means and Proportions
64. Verify that the sample size is large enough in each group to use the normal distribution to
construct a confidence interval for a difference in proportions.
Ans: pˆ SC = 133 = 0.409 = sample proportion of those with some college education
325
that believe in evolution
pˆ CG = 121 = 0.531 = sample proportion of the college graduates that believe in
228
evolution
Since all are greater than 10, the sample sizes are large enough to apply the Central
Limit Theorem and use a normal distribution to construct a confidence interval for
a difference in proportions.
Difficulty: Medium L.O.: 6.8.0
65. Construct a 90% confidence interval for the difference between the proportions of college
graduates and individuals with some college who believe in the theory of evolution.
Round your sample proportions and margin of error to three decimal places.
Ans: pˆ CG = 121 = 0.531 = sample proportion of the college graduates that believe in
228
evolution
pˆ SC = 133 = 0.409 = sample proportion of those with some college education
325
that believe in evolution
0.052 to 0.192
Difficulty: Medium L.O.: 6.8.1
Page 25
Random documents with unrelated
content Scribd suggests to you:
The Project Gutenberg eBook of The River
Motor Boat Boys on the Amazon; Or, The
Secret of Cloud Island
This ebook is for the use of anyone anywhere in the United
States and most other parts of the world at no cost and with
almost no restrictions whatsoever. You may copy it, give it away
or re-use it under the terms of the Project Gutenberg License
included with this ebook or online at www.gutenberg.org. If you
are not located in the United States, you will have to check the
laws of the country where you are located before using this
eBook.
Title: The River Motor Boat Boys on the Amazon; Or, The Secret
of Cloud Island
Language: English
By HARRY GORDON
Author of
“The River Motor Boat Boys on the Mississippi,”
“The River Motor Boat Boys on the Colorado,”
“The River Motor Boat Boys on the St. Lawrence,”
“The River Motor Boat Boys on the Columbia,”
“The River Motor Boat Boys on the Ohio.”
A. L. Burt Company
New York
Copyright, 1913
By A. L. Burt Company
TABLE OF CONTENTS
I. ALL READY FOR THE AMAZON
II. A CALL FROM THE DARKNESS
III. THE BROWN LEATHER BAG
IV. TWO GUESTS AND AN ARREST
V. THE BOY FROM PERU
VI. $500 REWARD—LIGHTS OF PARA
VII. A BOAT FROM THE SOUTH BRANCH
VIII. AN ADDITION TO THE PARTY
IX. AN ALARM IN THE NIGHT
X. A CAMPFIRE IN THE JUNGLE
XI. A HUMAN GUARD WITH HORNS
XII. A PLOT AGAINST THE RAMBLER
XIII. A PLEASANT SURPRISE
XIV. A BATTLE FOR THE BOAT
XV. THE VANISHING “CARGO”
XVI. “KEEP HER HEAD ON!”
XVII. NIGHTS ON THE AMAZON
XVIII. JUST AHEAD OF A MOB
XIX. THE SECRET OF CLOUD ISLAND
XX. A CALL FOR HELP
XXI. “A NICE, QUIET EXCURSION”
XXII. A BATH IN THE NIGHT
XXIII. CLOUD ISLAND