Unit 5
1. We take a random sample of 250 Canadians and ask them whether they attend a place
of worship (church, temple, mosque, synagogue, etc.). We would like to conduct a
hypothesis test of H0 : p = 0.3333 vs. Ha : p < 0.3333 to determine if there is evidence
that less than one-third of Canadians attend a place of worship. It is decided that H0
will be rejected if p̂ ≤ 0.2892. The level of significance of the test is closest to:
(A) 0.04 (B) 0.05 (C) 0.06 (D) 0.07 (E) 0.08
2. A local newspaper would like to estimate the true proportion of Winnipeggers who
approve of the job being done by the mayor. A random sample of Winnipeggers is
selected and each respondent is asked whether they approve of the job being done by
the mayor. When the newspaper reports the results of the poll, it states, “results are
accurate to within ± 3%, 19 times out of 20”. What sample size was used for this poll?
(A) 672 (B) 720 (C) 894 (D) 936 (E) 1068
3. A Tim Horton’s manager claims that more than 75% of customers purchase a coffee
when they visit the store. We take a random sample of 225 customers and find that 180
of them purchased a coffee. We would like to conduct a hypothesis test to determine
whether there is significant evidence to support the manager’s claim. The P-value for
the appropriate hypothesis test is:
(A) 0.0179 (B) 0.0256 (C) 0.0301 (D) 0.0359 (E) 0.0418
4. We would like to estimate the difference in the true proportions of Republicans and
Democrats who support Donald Trump. In a random sample of 280 Republicans, 238
said they support the president. In a random sample of 320 Democrats, 32 said they
support the president. The margin of error for a 90% confidence interval for pR − pD is:
(A) 0.0116 (B) 0.0226 (C) 0.0336 (D) 0.0446 (E) 0.0556
5. The Liquor Mart conducts a survey asking customers whether they prefer wine or beer.
In a random sample of 120 female customers, 72 say they prefer wine over beer. In
a random sample of 80 male customers, only 36 said they prefer wine over beer. We
conduct a hypothesis test of H0 : pf = pm vs. Ha : pf > pm to determine whether the true
proportion of female customers who prefer wine over beer is greater than that for male
customers. The value of the test statistic for the appropriate test of significance is:
(A) 2.09 (B) 2.23 (C) 2.47 (D) 2.61 (E) 2.85
6. A random sample of voters is selected from each of Canada’s three prairie provinces
(Manitoba, Saskatchewan and Alberta) and respondents are asked which federal political
party they support (Conservative, Green, Liberal or NDP). We would like to conduct
a test at the 10% level of significance to determine whether voters in Canada’s prairie
provinces are homogeneous with respect to which political party they support. What is
the critical value for the appropriate test of significance?
(A) 9.24 (B) 10.64 (C) 12.59 (D) 14.68 (E) 18.55
7. M & M’s chocolate candies come in six different colours. The official M & M’s website
claims the following colour distribution:
Colour Blue Orange Green Yellow Red Brown
Proportion of M & M’s 0.24 0.20 0.16 0.14 0.13 0.13
We take a random sample of 250 M & M’s and count the number of candies of each
colour. The sample data are shown below, as well as some cell chi-square values:
Colour Blue Orange Green Yellow Red Brown
Count 50 60 35 40 30 35
Expected ??? ??? ??? ??? ??? ???
Cell χ2 1.67 ??? 0.63 ??? 0.19 0.19
The value of the test statistic for the appropriate test of significance is:
(A) 3.86 (B) 4.04 (C) 4.45 (D) 4.97 (E) 5.39
2
8. The final exam in a university geography class has 125 multiple choice questions, each
with five possible choices (A, B, C, D, E). An unprepared student randomly guesses the
answer to each of the questions. What is the approximate probability that the student
gets at least 30 of the answers correct?
(A) 0.0068 (B) 0.0212 (C) 0.0643 (D) 0.1314 (E) 0.2206
9. We would like to estimate the true proportion of students at a large university who have
student loans. What sample size is required in order to estimate the true proportion to
within 0.05 with 98% confidence?
(A) 136 (B) 379 (C) 542 (D) 1127 (E) 2165
10. In a random sample of 250 Winnipeggers, 80 of them said they use transit. A 94%
confidence interval for the true proportion of all Winnipeggers who use transit is:
(A) (0.255, 0.385)
(B) (0.260, 0.380)
(C) (0.265, 0.375)
(D) (0.270, 0.370)
(E) (0.275, 0.365)
The next two questions (?? and ??) refer to the following:
A statistics professor at the University of Manitoba claims that more than 40% of stu-
dents who take STAT 1000 later take STAT 2000. We will conduct a hypothesis test to
investigate the professor’s claim.
11. In a random sample of 300 STAT 1000 students, it was found that 135 of them later
took STAT 2000. What is the P-value for the appropriate test of significance to test the
professor’s claim?
(A) 0.0384 (B) 0.0606 (C) 0.0934 (D) 0.1210 (E) 0.1539
3
12. We will make a Type II error in the previous hypothesis test if we conclude that:
(A) p̂ > 0.40 when in fact p̂ = 0.40.
(B) there is insufficient evidence that p > 0.40 when in fact this is the case.
(C) p > 0.40 when in fact p = 0.40.
(D) there is insufficient evidence that p̂ > 0.40 when in fact this is the case.
(E) p > 0.40 when in fact p < 0.40.
13. We would like to conduct a hypothesis test to determine whether the unemployment
rates differ for Canada and the United States. In a random sample of 450 Canadian
adults, 27 of them are unemployed. In a random sample of 300 American adults, 24 of
them are unemployed. We conduct a hypothesis test of H0 : pC = pU vs. Ha : pC 6= pU to
compare the unemployment rates in the two countries. The P-value for the appropriate
test of significance is:
(A) 0.0708 (B) 0.1423 (C) 0.1867 (D) 0.2514 (E) 0.2846
14. In a random sample of 600 Albertans, 306 say they support the Conservative Party. In
a random sample of 400 Manitobans, 180 say they support the Conservative Party. We
conduct a two-sample z test to determine if there is a difference in the true proportions
of Albertans and Manitobans who support the Conservative Party. The test statistic is
calculated to be z = 1.86 and the P-value is 0.0628. Suppose we had instead conducted
a chi-square test for homogeneity. The value of the test statistic and the P-value would
be, respectively,
(A) 1.86 and 0.0628.
(B) 1.86 and 0.0039.
(C) 1.36 and 0.0628.
(D) 3.46 and 0.0039.
(E) 3.46 and 0.0628.
4
The next two questions (?? and ??) refer to the following:
We would like to conduct a test of significance at the 10% level of significance to deter-
mine whether smoking behaviour of university students is independent of their parents’
smoking behaviour. The data is displayed in the table below, as well as some expected
cell counts and cell chi-square values:
Observed Student Student Row
Expected Smokes Doesn’t Smoke Total
Cell Chi-Square
Neither Parent 17 62 79
Smokes ??? ???
0.81 0.29
One Parent 11 40 51
Smokes ??? ???
0.51 ???
Both Parents 14 13 27
Smoke 7.22 19.78
??? 2.32
Column Total 42 115 157
15. What is the critical value for the appropriate test of significance?
(A) 4.61 (B) 5.99 (C) 7.78 (D) 9.24 (E) 10.64
16. What is the value of the test statistic for the appropriate test of significance?
(A) 4.92 (B) 6.54 (C) 8.17 (D) 10.49 (E) 12.31
17. According to the Hershey chocolate company, 50% of its Reese’s Pieces candies are
orange, 25% are yellow and 25% are brown. Suppose you take a random sample of 160
candies and find that 72 are orange, 56 are yellow and 32 are brown. We would like
to conduct a goodness of fit test to verify the company’s claim. The value of the test
statistic for the appropriate test of significance is:
(A) 8.8 (B) 9.2 (C) 9.8 (D) 10.2 (E) 10.8
5
18. You will flip a fair coin 200 times. What is the approximate probability you will get at
least 53% Heads?
(A) 0.8485 (B) 0.1711 (C) 0.8023 (D) 0.1977 (E) 0.1515
19. The editor of a scientific journal claims that less than 3% of Canadian adults have a
PhD. In a random sample of 5000 Canadian adults, it is found that 100 of them have
a PhD. What is the test statistic for the appropriate hypothesis test to investigate the
editor’s claim?
0.02 − 0.03
(A) r
(0.03)(0.97)
5000
0.03 − 0.02
(B) r
(0.02)(0.98)
5000
0.02 − 0.03
(C) r
(0.02)(0.03)
5000
0.03 − 0.02
(D) r
(0.03)(0.97)
5000
0.02 − 0.03
(E) r
(0.02)(0.98)
5000
20. We ask a random sample of 300 Winnipeg drivers if they have ever received a speeding
ticket. A confidence interval for the true proportion p of Winnipeg drivers who have
received a speeding ticket is calculated to be (0.3047, 0.3953). The confidence level of
this interval is closest to:
(A) 90% (B) 95% (C) 96% (D) 98% (E) 99%
6
21. We would like to construct a confidence interval for some population proportion p. For
which of the following combinations of confidence level, sample proportion and sample
size will the interval be the widest?
(A) 99% confidence, p̂ = 0.4, n = 300
(B) 99% confidence, p̂ = 0.3, n = 200
(C) 95% confidence, p̂ = 0.4, n = 300
(D) 95% confidence, p̂ = 0.3, n = 200
(E) 99% confidence, p̂ = 0.4, n = 200
22. We would like to estimate the true proportion of all Winnipeggers who read the Winnipeg
Free Press. What sample size is required to estimate this proportion to within 0.03 with
88% confidence?
(A) 612 (B) 632 (C) 672 (D) 652 (E) 692
23. We will take random samples of students from the University of Winnipeg and the
University of Manitoba, and we will conduct a test of H0 : pW = pM vs. Ha : pW > pM to
determine whether the true proportion of U of W students who take the bus to school
is greater than that for U of M students. We will commit a Type I error in this test if
we conclude that:
(A) pW > pM when in fact pM > pW .
(B) pM > pW when in fact pW > pM .
(C) pW > pM when in fact pW = pM .
(D) pW = pM when in fact pW > pM .
(E) pM > pW when in fact pW = pM .
7
The next two questions (?? and ??) refer to the following:
We would like to conduct a hypothesis test at the 1% level of significance to determine
whether music preference and movie preference are independent. A random sample of
200 adults is asked whether they prefer country, pop, or rock music, and whether they
prefer comedy, drama or horror movies. The results are displayed in the contingency
table below, with some expected counts and cell chi-square values:
Observed
Expected Country Pop Rock Row
Cell Chi-Square Total
Comedy 24 31 19 74
25.16 ??? ???
0.05 0.48 0.28
Drama 28 23 16 67
22.78 24.79 19.43
1.20 0.13 0.61
Horror 16 20 23 59
??? 21.83 ???
??? 0.15 ???
Column 68 74 58 200
Total
24. The P-value of the appropriate test of significance is:
(A) between 0.05 and 0.10.
(B) between 0.10 and 0.15.
(C) between 0.15 and 0.20.
(D) between 0.20 and 0.25.
(E) greater than 0.25.
8
25. What is the correct conclusion of the test?
(A) There is sufficient evidence that music preference and movie preference are inde-
pendent.
(B) There is sufficient evidence that music preference and movie preference are depen-
dent.
(C) There is insufficient evidence that music preference and movie preference are inde-
pendent.
(D) There is insufficient evidence that music preference and movie preference are de-
pendent.
(E) There is not enough information to draw a proper conclusion.
9
Answers
1. D 16. D
2. E 17. A
3. E 18. D
4. D 19. A
5. A 20. A
6. B 21. E
7. E 22. C
8. D 23. C
9. C 24. D
10. C 25. D
11. A
12. B
13. E
14. E
15. A
10