Unit 5 Practice Questions

1. (a) In Tim Horton’s annual “Roll up the Rim to Win” promotion, customers who
purchase a coffee can look under the rim to see if they have won a prize. According
to the company, one out of five cups is a winner. Over the course of the promotion,
one university student buys 100 cups of coffee. What is the probability that between
23% and 25% of them are winners?
(b) A retailer receives a large shipment of items from a manufacturer. The retailer will
test a random sample of 325 items, and will return the shipment if the proportion
of defective items in the sample is greater than 0.05. What is the probability the
shipment will be returned if the true proportion of defective items in the shipment
is 0.04?

2. We would like to construct a confidence interval to estimate the true proportion of all
Canadians with blue eyes.

(a) What sample size is required in order to estimate the true proportion to within
0.035 with 95% confidence?
(b) Using only the result from (a), what sample size is required to estimate the true
proportion to within 0.07 with 95% confidence?
(c) Suppose we believe that about 12% of Canadians have blue eyes. What sample
size is required in order to estimate the true proportion to within 0.035 with 95%
confidence?

3. We would like to estimate the true proportion p of all Canadian university students who
have ever smoked marijuana. In a random sample of 200 students, 118 of them report
to have tried the drug.

(a) Calculate a 90% confidence interval for the true proportion of all Canadian univer-
sity students who have smoked marijuana.
(b) We would like to conduct a hypothesis test at the 10% level of significance to deter-
mine whether there is evidence that the majority of Canadian university students
have tried marijuana. What are the hypotheses for the appropriate test of signifi-
cance?
(c) What is the value of the test statistic for the appropriate test of significance?
(d) What is the P-value of the test?
(e) What is the correct conclusion for the test?
(f) Suppose we had instead conducted the test using the critical value method. What
would be the decision rule and the conclusion?
 (g) What is the rejection rule in terms of p̂?
(h) What is the power of the test if the true proportion of students who have actually
tried marijuana is actually 0.6?

4. We would like to compare the proportion of Manitoba voters p1 and the proportion
of Ontario voters p2 who support the Conservative Party. In a random sample of 140
Manitoba voters, 58 said they support the Conservative Party. In a random sample of
180 Ontario voters, 63 said they support the Conservative Party.

(a) Calculate a 95% confidence interval for p1 − p2 , the difference in the proportions of
Manitoba and Ontario voters who support the Conservative Party.
(b) We would like to conduct a hypothesis test at the 5% level of significance to de-
termine whether there is evidence that support for the Conservative Party differs
among Manitoba and Ontario voters. Under the null hypothesis, we assume the pro-
portion of voters who support the Conservative Party is equal for the two provinces.
Calculate the pooled estimate of this common population proportion.
(c) What is the value of the test statistic for the appropriate test of significance?
(d) What is the P-value of the test?
(e) What is the correct conclusion for the test?
(f) Suppose we had instead conducted the test using the critical value method. What
would be the decision rule and the conclusion?
(g) Suppose we had instead conducted a chi-square test for homogeneity. What would
be the value of the test statistic and the P-value of the test?

5. (a) We would like to estimate the true proportion p of all Winnipeg drivers who have
received a speeding ticket. A random sample of Winnipeg drivers is selected, and a
99% confidence interval for p is calculated to be (0.63, 0.72). Provide an interpre-
tation of this confidence interval.
(b) We would like to conduct a hypothesis test to determine whether there is evidence
that the unemployment rates in the United States and Canada differ. In a random
sample of Americans, 9% are found to be unemployed. In a random sample of
Canadians, 8% are found to be unemployed. A hypothesis test is conducted, and
the P-value is calculated to be 0.2460. Provide an interpretation of this P-value.
6. We would like to compare the performance of three jockeys at a horse racing track.
Placings for horses ridden by the three jockeys for a sample of races are summarized in
the table below. (Assume that six horses run in each race.)

Placing Jockey A Jockey B Jockey C

1st 5 16 12
2nd 10 9 16
3rd 13 17 11
4th 9 12 7
5th 16 10 14
6th 17 6 10

(a) Conduct an appropriate hypothesis test at the 10% level of significance to determine
whether the three jockeys are homogeneous with respect to their performance. Use
the P-value method. Display the observed cell counts, the expected cell counts, and
the cell chi-square values in your contingency table.
(b) Show how the expected cell count and the cell chi-square values are calculated for
the number of races Jockey C finished in 5th Place.
(c) Provide an interpretation of the P-value of the test in (b).
(d) Which four cells contribute the most to the value of the test statistic?
(e) Suppose you had instead used the critical value method to conduct the test in (a).
What would be the decision rule and the conclusion of the test?
(f) Explain what it would mean to make a Type I Error and a Type II Error for this
hypothesis test.
7. An auto insurance company is conducting a study to examine the relationship between
the size of a car involved in an accident and the extent of damage caused to the car.
Data for a sample of claims are displayed in the table below:

Observed
Expected Minor Extensive Write-off Row Total
Cell Chi-Square Damage Damage
Compact 21 43 30 94
Midsize 25 51 58 134
Large 36 53 37 126
Column Total 82 147 125 354

We would like to conduct a chi-square test for independence at the 1% level of signifi-
cance.

(a) Find all expected cell counts and cell chi-square values in the table.
(b) What is the value of the test statistic for the appropriate test of significance?
(c) What is the P-value for the appropriate test of significance?
(d) What is the appropriate conclusion?
(e) Suppose we had instead conducted the test using the critical value method. What
would be the decision rule and the conclusion?
8. Based on her experience, a police officer in a large city believes that:

• Car accidents are least likely to occur during Fall.

• Accidents in Spring are twice as likely as in Fall.
• Accidents in Summer are three times as likely as in Fall.
• Accidents in Winter are four times as likely as in Fall.

The officer selects a random sample of accident reports and observes the season in which
each accident occurred. The data are summarized in the table below:

Season Spring Summer Fall Winter

# of Accidents 25 32 16 27

We would like to conduct a chi-square goodness of fit test at the 5% level of significance
to determine whether the officer’s proposed seasonal distribution of car accidents is
appropriate.
(a) Find all expected cell counts and cell chi-square values.
(b) What is the value of the test statistic for the appropriate test of significance?
(c) What is the P-value of the test?
(d) What is the appropriate conclusion for the test?
(e) Suppose we had instead conducted the test using the critical value method. What
would be the decision rule and the conclusion?