CH 12 Comparing Multiple Proportions Test of Independence and Goodness of Fit

CH 12 - Comparing Multiple Proportions, Test of Independence and Goodness of Fit
Multiple Choice
1. If there are three or more populations, then it is

a. possible to test for equality of three or more population proportions.
b. impossible to test for equality of the three population proportions, because chi-square tests deal with only two
populations.
c. customary to use a t distribution to test for equality of the three population proportions.
d. reasonable to test for equality of multiple population proportions using chi-square lower tail tests.
ANSWER: a
POINTS: 1
DIFFICULTY: Easy
LEARNING OBJECTIVES BSST.ASWC.17.12.01 - Testing the Equality of Population Proportions for Three or More
: Populations
NATIONAL STANDARDS United States - BUSPROG: Analytic
:
STATE STANDARDS: United States - AK - DISC: Hypothesis Testing
KEYWORDS: Bloom's: Remember
2. A population where each of its element is assigned to one and only one of several classes or categories is a
a. multinomial population.
b. Poisson population.
c. normal population.
d. binomial population.
ANSWER: a
POINTS: 1
DIFFICULTY: Easy
LEARNING OBJECTIVES: BSST.ASWC.17.12.03 - Goodness of Fit Test
NATIONAL STANDARDS: United States - BUSPROG: Analytic
STATE STANDARDS: United States - AK - DISC: Probability Distributions
3. The sampling distribution for a goodness of fit test is the

a. Poisson distribution.
b. t distribution.
c. normal distribution.
d. chi-square distribution.
ANSWER: d
POINTS: 1
DIFFICULTY: Easy
4. An important application of the chi-square distribution is

Copyright Cengage Learning. Powered by Cognero. Page 1
a. making inferences about a single population variance.
b. testing for goodness of fit.
c. testing for the independence of two categorical variables.
d. All of these alternatives are correct.
ANSWER: d
POINTS: 1
DIFFICULTY: Easy
LEARNING OBJECTIVES: BSST.ASWC.17.12.

United States - AK - DISC: Statistical Inference
5. The number of degrees of freedom associated with the chi-square distribution in a test of independence is
a. number of sample items minus 1.
b. number of populations minus 1.
c. number of rows minus 1 times number of columns minus 1.
d. number of populations minus number of estimated parameters minus 1.
ANSWER: c
POINTS: 1
DIFFICULTY: Easy
LEARNING OBJECTIVES: BSST.ASWC.17.12.02 - Test of Independence
6. A statistical test conducted to determine whether to reject or not reject a hypothesized probability distribution for a
population is known as a
a. comparison test.
b. probability test.
c. goodness of fit test.
d. normality test.
ANSWER: c
POINTS: 1
DIFFICULTY: Easy
KEYWORDS: Bloom's: Understand
7. The degrees of freedom for a data table with 12 rows and 12 columns is
a. 144.
b. 121.

c. 12.
d. 120.
ANSWER: b
POINTS: 1
DIFFICULTY: Easy
KEYWORDS: Bloom's: Apply
8. The degrees of freedom for a table with 6 rows and 3 columns is

a. 18.
b. 15.
c. 6.
d. 10.
ANSWER: d
POINTS: 1
DIFFICULTY: Easy
9. The degrees of freedom for a data table with 10 rows and 11 columns is
a. 100.
b. 110.
c. 21.
d. 90.
ANSWER: d
POINTS: 1
DIFFICULTY: Easy
10. Marascuilo procedure is used to test for a significant difference between pairs of population
a. proportions.
b. means.
c. variances.
d. standard deviations.
ANSWER: a
POINTS: 1
DIFFICULTY: Easy
: Populations
:
11. When individuals in a sample of 150 were asked whether or not they supported capital punishment, the following
information was obtained.
Do you support Number of
capital punishment? individuals
Yes 40
No 60
No Opinion 50
We are interested in determining whether or not the opinions of the individuals (as to Yes, No, and No Opinion) are
uniformly distributed. The expected frequency for each group is
a. .333.
b. .50.
c. 1/3.
d. 50.
ANSWER: d
POINTS: 1
DIFFICULTY: Easy
Yes 40
No 60
No Opinion 50
uniformly distributed. The calculated value for the test statistic equals
a. 2.
b. -2.
c. 20.
d. 4.
ANSWER: d
POINTS: 1
DIFFICULTY: Moderate
Yes 40
No 60
No Opinion 50
uniformly distributed. The number of degrees of freedom associated with this problem is
a. 150.
b. 149.
c. 2.
d. 3.
ANSWER: c
POINTS: 1
DIFFICULTY: Easy
Yes 40
No 60
No Opinion 50
uniformly distributed. The p-value is
a. larger than .1.
b. less than .01.
c. between .01 and .05.
d. between .05 and .1.
ANSWER: a
POINTS: 1
DIFFICULTY: Easy
Yes 40
No 60
No Opinion 50
uniformly distributed. The conclusion of the test at the 5% level of significance is that the
a. distribution is uniform.
b. null hypothesis cannot be rejected.
c. distribution might have been normal.
d. Marascuilo procedure is more applicable.
ANSWER: a
POINTS: 1
DIFFICULTY: Easy
16. Last school year, the student body of a local university consisted of 30% freshmen, 24% sophomores, 26% juniors,
and 20% seniors. A sample of 300 students taken from this year's student body showed the following number of students
in each classification.
Freshmen 83
Sophomores 68
Juniors 85
Seniors 64
We are interested in determining whether or not there has been a significant change in the classifications between the last
school year and this school year. The expected number of freshmen is
a. 83.
b. 90.
c. 30.
d. 10.
ANSWER: b
POINTS: 1
DIFFICULTY: Easy
Freshmen 83
Sophomores 68
Juniors 85
Seniors 64
school year and this school year. The expected frequency of seniors is
a. 60.
b. 20%.
c. 68.
d. 64.
ANSWER: a
POINTS: 1
DIFFICULTY: Easy
Freshmen 83
Sophomores 68
Juniors 85
Seniors 64
school year and this school year. The calculated value for the test statistic equals
a. .54.
b. .65.
c. 1.66.
d. 6.66.
ANSWER: c
POINTS: 1
Freshmen 83
Sophomores 68
Juniors 85
Seniors 64
school year and this school year. The p-value is
a. less than .005.
b. between .025 and .05.
c. between .05 and .1.
d. greater than .1.
ANSWER: d
POINTS: 1
DIFFICULTY: Easy
Freshmen 83
Sophomores 68
Juniors 85
Seniors 64
school year and this school year. At a .05 level of significance, the null hypothesis
a. should not be rejected.
b. should be rejected.
c. was designed wrong.
d. cannot be tested.
ANSWER: a
POINTS: 1
DIFFICULTY: Easy
21. In the past, 35% of the students at ABC University were in the Business College, 35% of the students were in the
Liberal Arts College, and 30% of the students were in the Education College. To see whether or not the proportions have
changed, a sample of 300 students from the university was taken. Ninety of the sample students are in the Business
College, 120 are in the Liberal Arts College, and 90 are in the Education College. This problem is an example of a
a. z test for proportions.
b. test for independence.
c. Marascuilo procedure.
d. multinomial population.
ANSWER: d
POINTS: 1
DIFFICULTY: Easy
College, 120 are in the Liberal Arts College, and 90 are in the Education College. The expected frequency for the
Business College is
a. .3.
b. .35.
c. 90.
d. 105.
ANSWER: d
POINTS: 1
DIFFICULTY: Easy
College, 120 are in the Liberal Arts College, and 90 are in the Education College. The calculated value for the test statistic
equals
a. .01.
b. .75.
c. 4.29.
d. 4.38.
ANSWER: c
POINTS: 1

College, 120 are in the Liberal Arts College, and 90 are in the Education College. The hypothesis is to be tested at the 5%
level of significance. The critical value from the table equals
a. 7.378.
b. 9.348.
c. 5.991.
d. 7.815.
ANSWER: c
POINTS: 1
DIFFICULTY: Easy
College, 120 are in the Liberal Arts College, and 90 are in the Education College. Using α = .05, the conclusion of the test
is that the
a. null hypothesis cannot be rejected.
b. proportions have not changed significantly.
c. proportions follow normal distribution.
d. Marascuilo procedure is more applicable.
ANSWER: b
POINTS: 1
DIFFICULTY: Easy
26. The table below gives beverage preferences for random samples of teens and adults.
Teens Adults Total
Coffee 50 200 250
Tea 100 150 250
Soft Drink 200 200 400
Other 50 50 100
400 600 1000
We are asked to test for independence between age (i.e., adult and teen) and drink preferences. With a .05 level of
significance, the critical value for the test is
a. 5.991.
b. 7.815.
c. 14.067.
d. 15.507.
ANSWER: b
POINTS: 1
DIFFICULTY: Easy
Teens Adults Total
Coffee 50 200 250
Tea 100 150 250
Other 50 50 100
400 600 1000
We are asked to test for independence between age (i.e., adult and teen) and drink preferences. The expected number of
adults who prefer coffee is
a. .25.
b. .33.
c. 150.
d. 200.
ANSWER: c
POINTS: 1
DIFFICULTY: Easy
Teens Adults Total
Coffee 50 200 250
Tea 100 150 250
Other 50 50 100
400 600 1000
We are asked to test for independence between age (i.e., adult and teen) and drink preferences. The test statistic for this
test of independence is
a. 0.
b. 8.4.
c. 62.5.
d. 82.5.
ANSWER: c
POINTS: 1
29. The owner of a car wash wants to see if the arrival rate of cars follows a Poisson distribution. In order to test the
assumption of a Poisson distribution, a random sample of 150 ten-minute intervals was taken. You are given the following
observed frequencies:
Number of Cars Arriving
Frequency
in a 10-Minute Interval
0 3
1 10
2 15
3 23
4 30
5 24
6 20
7 13
8 8
9 or more 4
150
Calculate mean and use Poisson probabilities. The expected frequency of exactly 3 cars arriving in a 10-minute interval is
a. .1533.
b. .1743.
c. 23.
d. 26.145.
ANSWER: d
POINTS: 1
Frequency
0 3
1 10
2 15
3 23
4 30
5 24
6 20
7 13
8 8
9 or more 4
150
The calculated value for the test statistic equals

a. 3.11.
b. .18.
c. 1.72.
d. 2.89.
ANSWER: d
POINTS: 1
Frequency
0 3
1 10
2 15
3 23
4 30
5 24
6 20
7 13
8 8
9 or more 4
150
The p-value is
a.
greater than .1.
b.
between .05 and .1.
c.
between .025 and .05.
d.
less than .01.
ANSWER: a
POINTS: 1
DIFFICULTY: Easy
Frequency
0 3
1 10
2 15
3 23
4 30
5 24
6 20
7 13
8 8
9 or more 4
150
At the .05 level of significance, the conclusion of the test is that the
b. arrival of cars does not follow a Poisson distribution.
c. 10-minute intervals follow a Poisson distribution.
d. arrival of cars has no distribution.
ANSWER: a
POINTS: 1
DIFFICULTY: Easy
33. You want to test whether or not the following sample of 30 observations follows a normal distribution. The mean of
the sample equals 11.83 and the standard deviation equals 4.53.
2 3 5 5 7 8 8 9 9 10
11 11 12 12 12 12 13 13 13 14
15 15 15 16 16 17 17 18 18 19
The number of intervals or categories used to test the hypothesis for this problem is
a. 4.
b. 5.
c. 6.
d. 10.
ANSWER: c
POINTS: 1
DIFFICULTY: Easy
2 3 5 5 7 8 8 9 9 10
11 11 12 12 12 12 13 13 13 14
15 15 15 16 16 17 17 18 18 19
The expected frequency in the 3rd interval is

a. 3.
b. 4.
c. 5.
d. 10.
ANSWER: c
POINTS: 1
DIFFICULTY: Easy
2 3 5 5 7 8 8 9 9 10
11 11 12 12 12 12 13 13 13 14
15 15 15 16 16 17 17 18 18 19
The calculated value for the test statistic equals

a. 0.
b. 1.67.
c. 2.
d. 6.
ANSWER: c
POINTS: 1
2 3 5 5 7 8 8 9 9 10
11 11 12 12 12 12 13 13 13 14
15 15 15 16 16 17 17 18 18 19
The p-value is
a.
greater than .1.
b.
between .05 and .1.
c.
between .025 and .05.
d.
less than .005.
ANSWER: a
POINTS: 1
DIFFICULTY: Easy
2 3 5 5 7 8 8 9 9 10
11 11 12 12 12 12 13 13 13 14
15 15 15 16 16 17 17 18 18 19
At the 5% level of significance, the conclusion of the test is that the

b. data does not follow a normal distribution.
c. sample data has no probability distribution.
d. sample data is incorrect.
ANSWER: a
POINTS: 1
DIFFICULTY: Easy
38. The following table shows the number of individuals in a sample of 300 who indicated they support the new tax
proposal.
Political Party Support
Democrats 100
Republicans 120
Independents 80
We are interested in determining whether or not the opinions of the individuals of the three groups are uniformly
distributed. The expected frequency for each group is
a. .333.
b. .50.
c. 50.
d. 100.
ANSWER: d
POINTS: 1
DIFFICULTY: Easy
proposal.
Democrats 100
Republicans 120
Independents 80
distributed. The calculated value for the test statistic equals
a. 2.
b. 4.
c. 0.
d. 8.
ANSWER: d
POINTS: 1
proposal.
Democrats 100
Republicans 120
Independents 80
distributed. The number of degrees of freedom associated with this problem is
a. 2.
b. 3.
c. 300.
d. 299.

ANSWER: a
POINTS: 1
DIFFICULTY: Easy
41. The test statistic for goodness of fit has a chi-square distribution with k - 1 degrees of freedom provided that the
expected frequencies for all categories are
a. 5 or more.
b. 10 or more.
c. k or more.
d. 2k.
ANSWER: a
POINTS: 1
DIFFICULTY: Easy
42. The test for goodness of fit

a. is always a lower tail test.
b. is always an upper tail test.
c. is always a two-tailed test.
d. can be a lower or an upper tail test.
ANSWER: b
POINTS: 1
DIFFICULTY: Easy
43. The number of categorical outcomes per trial for a multinomial probability distribution is

a. two or more.
b. three or more.
c. four or more.
d. five or more.
ANSWER: b
POINTS: 1
DIFFICULTY: Easy
44. The test for goodness of fit, test of independence, and test of multiple proportions are designed for use with
a. categorical data.
b. bivariate data.
c. quantitative data.
d. ordinal data.
ANSWER: a
POINTS: 1
DIFFICULTY: Easy
LEARNING OBJECTIVES: BSST.ASWC.17.12.
45. The properties of a multinomial experiment include all of the following except

a. the experiment consists of a sequence of n identical trials.
b. three or more outcomes are possible on each trial.
c. the probability of each outcome can change from trial to trial.
d. the trials are independent.
ANSWER: c
POINTS: 1
DIFFICULTY: Easy
Subjective Short Answer
46. Shoppers were asked about their regular grocery shopping locations. The table below shows the responses of the
sampled shoppers. We are interested in determining if the proportions of females in the three categories are different from
each other.
Grocery Discount Membership

Gender chain store warehouse Total
Female 230 80 100 410
Male 80 50 60 190
Total 310 130 160 600
a. Provide the null and alternative hypotheses.

b. Determine the expected frequencies.
c. Compute the sample proportions.
d. Compute the critical values (CVij).
e. Give your conclusions by providing numerical reasoning.
ANSWER: a.
H0: p1 = p2 = p3
Ha: Not all population proportions are equal
b.
Grocery Chain Discount Store Membership Warehouse
Female 211.833 88.833 109.333 410
Male 98.167 41.167 50.667 190
310 130 160 600
c.
= .7419
= .6154
= .6250
d.
CV12 = .12087
CV13 = .11170
CV23 = .14030
e.
Pairwise comparison | - | CVij Sig. if | - | > CVij
1 Vs. 2 .1266 .12087 Significant
2 Vs. 3 .0096 .14030 Not significant
POINTS: 1
DIFFICULTY: Challenging
: Populations
:
KEYWORDS: Bloom's: Apply | Bloom's: Understand
47. The following table shows the results of a study on smoking and three illnesses. We are interested in determining if
the proportions of smokers in the three categories are different from each other.
Emphysema Heart problem Cancer Total

Smoker 150 70 100 320
Non-smoker 50 130 500 680
Total 200 200 600 1000
a. Provide the null and alternative hypotheses.

b. Determine the expected frequencies.
c. Compute the sample proportions.
d. Compute the critical values (CVij).
e. Give your conclusions by providing numerical reasoning.
ANSWER: a.
H0: p1 = p2 = p3
Ha: Not all population proportions are equal
b.
Emphysema Heart problem Cancer Total
Smoker 64 64 192 320
Non-smoker 136 136 408 680
Total 200 200 600 1000
c.
.7500
.3500
.1667
d.
CV12 .11150
CV13 .08369
CV23 .09057
e.
Pairwise Comparison | - | CVij Sig. if (| - |) > CVij
POINTS: 1
LEARNING OBJBSST.ASWC.17.12.01 - Testing the Equality of Population Proportions for Three or More Populations
ECTIVES:
NATIONAL STA United States - BUSPROG: Analytic
NDARDS:
STATE STANDA United States - AK - DISC: Hypothesis Testing
RDS:
48. Prior to the start of the season, it was expected that audience proportions for the four major news networks would be
CBS - 18.6%, NBC - 12.5%, ABC - 28.9%, and BBC - 40%. A recent sample of homes yielded the following viewing
audience data.
Observed Frequencies (fi)

CBS 400
NBC 230
ABC 560
BBC 810
Total 2000
We want to determine whether or not the recent sample supports the expectations of the number of homes of the viewing
audience of the four networks.
a. State the null and alternative hypotheses to be tested.

b. Compute the test statistic.
c. The null hypothesis is to be tested at the 5% level of significance. Determine the critical value for this test.
d. What do you conclude?
ANSWER: H0: p1 = .186, p2 = .125, p3 = .289, p4 = .4
a.
Ha: Proportions are not as stated in H0
b. Test statistic = 4.39
c. Critical value = 7.815
Do not reject H0; there is no evidence that the proportions are different from those stated
d.
in H0.
POINTS: 1
LEARNING OBJECTIVES BSST.ASWC.17.12.03 - Goodness of Fit Test
:

49. Prior to the start of the season, it was expected that audience proportions for the four major news networks would be
CBS - 28%, NBC - 35%, ABC - 22%, and BBC - 15%. A recent sample of homes yielded the following viewing
audience data.
Number of Homes
CBS 850
NBC 980
ABC 670
BBC 500
We want to determine whether or not the recent sample supports the expectations of the number of homes of the viewing
audience of the four networks.
c. The null hypothesis is to be tested at a 5% level of significance. Determine the critical value for this test.
ANSWER: H0: p1 = .28, p2 = .35, p3 = .22, p4 = .15
a.
Ha: Proportions are not as stated in H0
b. Test statistic = 10.49
c. Critical chi-square = 7.815
d. Reject H0 and conclude that the proportions are different from those stated in H0.
POINTS: 1
:

50. The results of a recent study regarding smoking and three types of illness are shown in the following table.
Illness Non-Smokers Smokers Totals

Emphysema 50 150 200
Heart problem 50 150 200
Cancer 100 500 600
Totals 200 800 1000
We are interested in determining whether or not illness is independent of smoking.

b. Show the table of the expected frequencies and determine the test statistic.
c. The null hypothesis is to be tested at the .05 level. Determine the critical value for this test.
ANSWER: a.
H0: Illness is independent of smoking
Ha: Illness is not independent of smoking
b.
Emphysema 40 160 200
Cancer 120 480 600
Totals 200 800 1000
Chi-square = 10.42
c. Critical chi-square = 5.991

d. Reject the H0; therefore, illness is not independent of smoking.
POINTS: 1


51. In the last presidential election, before the candidates started their major campaigns, the percentages of registered
voters who favored the various candidates were as follows.
Percentages
Republicans 34%
Democrats 43%
Independents 23%
After the major campaigns began, a random sample of 400 voters showed that 172 favored the Republican candidate; 164
were in favor of the Democratic candidate; and 64 favored the Independent candidate. We are interested in determining
whether the proportion of voters who favored the various candidates had changed.
a. Compute the test statistic.

b. Using the p-value approach, test to see if the proportions have changed. Let α = .01.
c. Using the critical value approach, test the hypotheses. Use α = .01.
ANSWER: a. χ2 = 18.42
b. p-value < .005, reject H0; the proportions have changed.
2
c. χ = 18.42 > 9.210; reject H0; the proportions have changed.
POINTS: 1
:

52. During the first few weeks of the new television season, the evening news audience proportions were recorded as
ABC - 31%, CBS - 34%, and NBC - 35%. A sample of 600 homes taken recently yielded the following viewing audience
data.
Number of Homes
ABC 150
CBS 200
NBC 250
We want to determine whether or not there has been a significant change in the proportion of viewing audience of the
three networks.
b. Compute the expected frequencies.
c. Compute the test statistic.
The null hypothesis is to be tested at the .05 level of significance. Determine the critical value for this test. What do
d.
you conclude?
e. Determine the p-value and perform the test.
ANSWER: a. H0: There has not been a change

Ha: There has been a change

Expected Frequencies
186
b.
204
210
c. Chi-square = 14.67
d. Critical value = 5.991. Reject the null hypothesis. There has been a significant change.
e. p-value < .005 (actual p-value using Excel = .0007), reject H0.
POINTS: 1
:

53. The results of a recent study regarding smoking and three types of illness are shown in the following table.
Emphysema 20 60 80
Cancer 30 40 70
Totals 120 180 300
We are interested in determining whether or not illness is independent of smoking.

b. Show the table of the expected frequencies.
d. The null hypothesis is to be tested at the 5% level. Determine the critical value for this test. What do you conclude?
ANSWER: H0: Illness is independent of smoking
a.
Ha :Illness is not independent of smoking
b.
Expected Frequencies
Emphysema 32 48 80
Cancer 28 42 70
Totals 120 180 300
c. Test statistic = 10.52

d. Critical chi-square = 5.991; reject H0 and conclude illness is not independent of smoking.

e. p-value is between .01 and .005 (actual p-value using Excel is .0052); reject H0.
POINTS: 1
LEARNING OBJECTIVES BSST.ASWC.17.12.02 - Test of Independence
:

54. Among 1000 managers with degrees in business administration, the following data have been accumulated as to their
fields of concentration.
Major Top Management Middle Management TOTAL
Management 280 220 500
Marketing 120 80 200
Accounting 150 150 300
TOTAL 550 450 1000
We want to determine if the position in management is independent of field (major) of concentration.

b. Using the p-value approach at the 10% level, test to determine if management position is independent of major.
c. Using the critical value approach, test the hypotheses. Let α = .10.
ANSWER: a. χ2 = 5.25
b. p-value is between .05 and .10; reject H0; position is not independent of major.
c. χ2 = 5.25 > 4.605; reject H0; the position is not independent of the major.
POINTS: 1
:

55. From a poll of 800 television viewers, the following data have been accumulated as to their levels of education and
their preference of television stations. We are interested in determining if the selection of a TV station is independent of
the level of education.
Educational Level
High School Bachelor Graduate TOTAL
Public Broadcasting 50 150 80 280
Commercial Stations 150 250 120 520
TOTAL 200 400 200 800
a. State the null and alternative hypotheses.

b. Show the table of the expected frequencies.
d. The null hypothesis is to be tested at the 5% level of significance. Determine the critical value for this test.
ANSWER: a.
H0: Selection of TV station is independent of level of education
Ha :Selection of TV station is not independent of level of education
b.
TOTAL 200 400 200 800

c. Test statistic = 12.09
d. Critical chi-square = 5.991;
reject H0 and conclude selection of TV station is not independent of level of education.
e. p-value < .005 (actual p-value using Excel is .0024); reject H0.
POINTS: 1

LEARNING O BSST.ASWC.17.12.02 - Test of Independence
BJECTIVES:
NATIONAL ST United States - BUSPROG: Analytic
ANDARDS:
STATE STAND United States - AK - DISC: Hypothesis Testing
ARDS:
56. Before the start of the Winter Olympics, it was expected that the percentages of medals to be awarded to the top
contenders is as follows.
Percentages
United States 25%
Germany 22%
Norway 18%
Austria 14%
Russia 11%
France 10%
Midway through the Olympics, of the 120 medals awarded, the following distribution was observed.
Number of Medals
United States 33
Germany 36
Norway 18
Austria 15
Russia 12
France 6
We want to test if there is a significant difference between the expected and actual awards given.
Using the p-value approach, test to see if there is a significant difference between the expected and the actual values.
b.
Let α = .05.
c. At the 5% level of significance, test for a significant difference using the critical value approach.
ANSWER:
a. χ2 = 7.69
b. p-value is larger than .10; do not reject H0; no evidence of a significant difference
c. critical χ2 = 11.070; do not reject H0
POINTS: 1
LEARNING O BSST.ASWC.17.12.03 - Goodness of Fit Test
BJECTIVES:
ANDARDS:
ARDS:
57. A medical journal reported the following frequencies of deaths due to cardiac arrest for each day of the week:
Cardiac Death by Day of the Week
Day f
Monday 40
Tuesday 17
Wednesday 16
Thursday 29
Friday 15
Saturday 20
Sunday 17
We want to determine whether the proportion of deaths is uniform over the week.
b. Using the p-value approach at the .05 level of significance, test for the uniformity of deaths over the week.
c. Using the critical value approach, perform the test for uniformity. Use α = .05.
ANSWER:
a. χ2 = 23.27
b. p-value is less than .005; reject H0; the distribution is not uniform.
c. critical χ2 = 12.592; reject H0
POINTS: 1
:

58. Before the presidential debates, it was expected that the percentages of registered voters in favor of various candidates
would be as follows.
Percentages
Democrats 48%
Republicans 38%
Independent 4%
Undecided 10%
After the presidential debates, a random sample of 1200 voters showed that 540 favored the Democratic candidate; 480
were in favor of the Republican candidate; 40 were in favor of the Independent candidate; and 140 were undecided. We
want to see if the proportion of voters has changed.
b. Use the p-value approach to test the hypotheses. Let α = .05.
c. Using the critical value approach, test the hypotheses. Let α = .05.
ANSWER:
a. χ2 = 8.18
b. p-value is between .025 and .05; reject H0; there has been a change.
c. critical value is 7.815; reject H0; there has been a change.
POINTS: 1
:

59. Last school year, in the school of Business Administration, 30% were Accounting majors; 24% Management majors;
26% Marketing majors; and 20% Economics majors. A sample of 300 students taken from this year's students of the
school showed the following number of students in each major:
Accounting 83
Management 68
Marketing 85
Economics 64
Total 300
We want to see if there has been a significant change in the proportion of students in each major.
Has there been any significant change in the proportion of students in each major between the last school year and
b.
this school year? Use the p-value approach and let α = .05.
ANSWER:
a. χ2 = 1.66
b. p-value is greater than .1; do not reject H0; no evidence of any significant change
POINTS: 1
:

60. The personnel department of a large corporation reported sixty resignations during the last year. The following table
groups these resignations according to the season during which they occurred:
Season Number of Resignations
Winter 10
Spring 22
Summer 19
Fall 9
Test to see if the proportion of resignations is uniform over the four seasons.
Let α = .05.
ANSWER: χ2 = 8.41 (rounded); p-value is between .025 and .05; reject H0; the distribution is not
uniform.
POINTS: 1
61. In 2002, 40% of the students at a major university were Business majors, 35% were Engineering majors, and the rest
of the students were majoring in other fields. In a sample of 600 students from the same university taken in 2003, 200
were Business majors, 220 were Engineering majors, and the remaining students in the sample were majoring in other
fields. Using α = .05, test to see if there has been a significant change in the proportions between 2002 and 2003.
ANSWER: 2
χ = 13.15 (rounded); p-value is less than .005; thus, reject H0 and conclude there has been a
significant change.
POINTS: 1
LEARNING OBJECTIV BSST.ASWC.17.12.03 - Goodness of Fit Test
ES:
NATIONAL STANDAR United States - BUSPROG: Analytic
DS:
62. Before the rush began for Christmas shopping, a department store had noted that the percentage of its customers who
use the store's credit card, the percentage of those who use a major credit card, and the percentage of those who pay cash
are the same. During the Christmas rush, in a sample of 150 shoppers, 46 used the store's credit card; 43 used a major
credit card; and 61 paid cash. With α = .05, test to see if the methods of payment have changed during the Christmas rush.
ANSWER: χ2 = 3.72; p-value is larger than .10; no evidence of change
POINTS: 1

63. A major automobile manufacturer claimed that the frequencies of repairs on all five models of its cars are the same. A
sample of 200 repair services showed the following frequencies on the various makes of cars.
Model of Car Frequency
A 32
B 45
C 43
D 34
E 46
At α = .05, test the manufacturer's claim.

ANSWER: χ2 = 4.25; p-value is larger than .1; do not reject H0; no evidence of difference
POINTS: 1
64. A lottery conducted involves the random selection of numbers from 0 to 4. To make sure that the lottery is fair, a
sample of 250 was taken. The following results were obtained:
Value Frequency
0 40
1 45
2 55
3 60
4 50

c. The null hypothesis is to be tested at the 5% level of significance. Determine the critical value from the table.
d. What do you conclude about the fairness of this lottery?
ANSWER:
H0: p0 = p1 = p2 = p3 = p4 = .2
a.
Ha: The population proportions are not p0 = p1 = p2 = p3 = p4 = .2
b. 5
c. 9.488
d. Do not reject the null hypothesis; there is no evidence that the lottery is not fair.
POINTS: 1
:

65. The management of Compute-All know that in the past, 40% of their sales were from people under 30 years old, 45%
of their sales were from people who are between 30 and 50 years old, and 15% of their sales were from people who are
over 50 years old. A sample of 300 customers was taken to see if these market shares had changed. In the sample, 100
people were under 30 years old, 150 people were between 30 and 50 years old, and 50 people were over 50 years old.
c. The null hypothesis is to be tested at the 1% level of significance. Determine the critical value from the table.
ANSWER:
H0: p1 = .4, p2 = .45, and p3 = .15
a.
Ha: The population proportions are not p1 = .4, p2 = .45, and p3 = .15
b. 5.56
c. 9.210
d. Do not reject the null hypothesis; there is no evidence that the market shares had changed.
POINTS: 1
:

66. The following table shows the results of recent study regarding gender of individuals and their selected field of study.
Field of study Male Female TOTAL
Medicine 80 40 120
Business 60 20 80
Engineering 160 40 200
TOTAL 300 100 400
We want to determine if the selected field of study is independent of gender.

b. Using the p-value approach at α = .10, test to see if the field of study is independent of gender.
c. Using the critical value approach at α = .10, test for the independence of selected major and gender.
ANSWER:
a. χ2 = 7.11
b. p-value is between .025 and .05; reject H0; field of study is not independent of gender.
c. critical χ2 = 4.605; reject H0; selected major and gender are not independent.
POINTS: 1
BJECTIVES:
ANDARDS:
ARDS:

67. Shown below is 3 x 2 table with observed values from a sample of 1500. At the 5% level of significance, test for
independence of the row and column factors.
Column Factor
Row Factor X Y Total
A 450 300 750
B 300 300 600
C 100 50 150
Total 850 650 1500
ANSWER: χ2 = 20.36; p-value is less than .005; not independent
POINTS: 1
68. Shown below is a 2 x 3 table with observed values from a sample of 500. At α = .05 using the critical value approach,
test for independence of the row and column factors.
Column Factor
Row Factor X Y Z
A 40 50 110
B 60 100 140
ANSWER: χ2 = 4.44 < 5.991; no evidence that row and column factors are not independent.
POINTS: 1
69. A sample of 150 individuals (males and females) was surveyed, and the individuals were asked to indicate their yearly
incomes. Their incomes were categorized as follows.
Category 1 $20,000 up to $40,000
Category 2 $40,000 up to $60,000
Category 3 $60,000 up to $80,000
The results of the survey are shown below.

Income Category Male Female
Category 1 10 30
Category 2 35 15
Category 3 15 45
We want to determine if yearly income is independent of gender.

b. Using the p-value approach, test to determine if yearly income is independent of gender. Use α = .05.
ANSWER:
a. χ2 = 28.13
b. p-value is less than .005; thus, reject H0 and conclude income is not independent of gender.
POINTS: 1
BJECTIVES:
ANDARDS:
ARDS:
70. A group of 2000 individuals from 3 different cities were asked whether they owned a foreign or a domestic car. The
following table shows the results of the survey.
CITY
Type of Car Detroit Atlanta Denver Total
Domestic 80 200 520 800
Foreign 120 600 480 1200
Total 200 800 1000 2000
At α = .05 using the p-value approach, test to determine if the type of car purchased is independent of the city in which the
purchasers live.
ANSWER: χ2 = 135; p-value is almost zero; thus, reject H0 and conclude that the type of car purchased is not
independent of the city.
POINTS: 1
LEARNING OBJECTI BSST.ASWC.17.12.02 - Test of Independence
VES:
DS:
71. Dr. Maria Pecora diet pills are supposed to cause significant weight loss. The following table shows the results of a
recent study where some individuals took the diet pills and some did not.
Diet Pills No Diet Pills Total
No Weight Loss 80 20 100
Weight Loss 100 100 200
Total 180 120 300
We want to see if losing weight is independent of taking the diet pills.

Using the p-value approach at the 5% level of significance, test to determine if weight loss is independent of taking
b.
the pill.
c. Use the critical value approach and test for independence. Let α = .05.
ANSWER:
a. χ2 = 25
b. p-value is less than .005 (almost zero); weight loss is not independent of taking the pills.
c. critical χ2 = 3.841; not independent
POINTS: 1
:

72. Five hundred randomly selected automobile owners were questioned on the main reason they had purchased their
current automobile. The results are given below.
Styling Engineering Fuel Economy Total
Male 70 130 150 350
Female 30 20 100 150
Total 100 150 250 500
a. State the null and alternative hypotheses for an independence test.

b. State the decision rule for the critical value approach. Let α = .01.
c. Calculate the χ2 test statistic.
d. Give your conclusion for this test.
ANSWER:
a. H0: automobile preference is independent of gender
Ha: automobile preference is not independent of gender
Do not reject H0 if χ2 < 9.210
b.
Reject H0 if χ2 ≥ 9.210
c. 31.75
d. Reject the null hypothesis; automobile preference is not independent of gender.
POINTS: 1

BJECTIVES:
ANDARDS:
ARDS:
73. A group of 500 individuals were asked to cast their votes regarding a particular issue of the Equal Rights Amendment.
The following table shows the results of the votes:
Sex Favor Undecided Oppose TOTAL
Female 180 80 40 300
Male 150 20 30 200
TOTAL 330 100 70 500
At α = .05 using the p-value approach, test to determine if the votes cast were independent of the sex of the individuals.
ANSWER: χ2 = 21; p-value is less than .005; votes are not independent of sex.
POINTS: 1
74. Two hundred fifty managers with degrees in business administration indicated their fields of concentration as shown
below.
Major Top Management Middle Management TOTAL
Management 65 60 125
Marketing 30 20 50
Accounting 25 50 75
TOTAL 120 130 250
At α = .01 using the p-value approach, test to determine if the position in management is independent of the major of
concentration.
ANSWER: χ2 = 10.15; p-value is between .005 and .01; reject H0; the position is not independent of
major.
POINTS: 1

75. From a poll of 800 television viewers, the following data have been accumulated as to their levels of education and
their preference of television stations.
Level of Education
TOTAL 190 410 200 800
Test at α = .05 to determine if the selection of a TV station is dependent upon the level of education. Use the p-value
approach.
ANSWER: χ2 = 6.93; p-value is between .025 and .05; reject H0; selection of TV station is not independent of
the level of education.
POINTS: 1

LEARNING OBJECTI BSST.ASWC.17.12.02 - Test of Independence
VES:
DS:
76. The data below represents the fields of specialization for a randomly selected sample of undergraduate students. We
want to determine whether there is any dependency between the fields of specialization and the regions of the country.
Northeast Midwest South West Total
Business 54 65 28 93 240
Engineering 15 24 8 33 80
Liberal Arts 65 84 33 98 280
Fine Arts 13 15 7 25 60
Health Sciences 3 12 4 21 40
150 200 80 270 700
a. Determine the critical value of the chi-square χ2 for this test of independence.
b. Calculate the value of the test statistic.
c. What is the conclusion for this test? Let α = .05.
ANSWER:
a. 21.026
b. 9.64 (rounding off the expected frequencies)
c. Do not reject the null hypothesis that fields of specialization and region are independent.
POINTS: 1
:

77. A department store believes that telephone calls come into the switchboard at 10-minute intervals, according to a
Poisson distribution. Before ordering new equipment, the store wishes to determine whether the Poisson model is a valid
assumption. Records on the number of calls received were kept for a random selection of 150 ten-minute intervals. The
results are shown below.
Number of Calls Frequency
0 5
1 18
2 24
3 30
4 32
5 13
6 20
7 or more 8
150
a. What is the average number of calls during these 10-minute intervals?

b. Generate the expected number of calls using a Poisson probability table.
c. Give the null and alternative hypotheses for the appropriate test.
d. Determine the number of degrees of freedom for this test.
e. Calculate the value of the test statistic.
Determine the p-value and state whether or not the Poisson model is a valid model for the
f.
phone calls. Let α = .10.
ANSWER:
a. 3.5
b.
Number of
Calls ei
0 or 1 20.385
2 27.750
3 32.370
4 28.320
5 19.830
6 11.565
7 or more 9.780

c. H0: The number of telephone calls during a 10-minute interval follows a Poisson distribution
Ha: The number of telephone calls during a 10-minute interval does not follow a Poisson
distribution
d. 5
e. χ2 = 10.32
f. p-value is between .05 and .10; reject the null hypothesis; the Poisson distribution is not a
valid model.
POINTS: 1
LEARNING OBJECTIVE BSST.ASWC.17.12.03 - Goodness of Fit Test
S:
:
78. It is believed that sales of books at a local bookstore follow a Poisson distribution. Below you are given information
on the number of books sold during a sample of 120 fifteen-minute intervals.
Number of Books Frequency
0 2
1 3
2 12
3 16
4 19
5 20
6 18
7 16
8 9
9 or more 5
120
a. What is the average number of books sold during a 15-minute period?

b. Using the Poisson distribution, find the probability associated with the number of books sold.
c. Generate the expected number of books sold using a Poisson probability table.
d. State the null and alternative hypotheses.
e. Calculate the test statistic.
f. Use the p-value approach to test the hypotheses. What is your conclusion? Let α = .05.
ANSWER: a. 4.9
b.
Number of Books Poisson Probability
0 or 1 0.0439
2 0.0894
3 0.1460
4 0.1789
5 0.1753
6 0.1432
7 0.1002
8 0.0614
9 or more 0.0617
c.
Number of Books ei
0 or 1 5.268
2 10.728
3 17.520
4 21.468
5 21.036
6 17.184
7 12.024
8 7.368
9 or more 7.404

H0: The number of books sold in a 15-minute interval follows a Poisson distribution
d.
Ha: The number of books sold in a 15-minute interval does not follow a Poisson distribution
e. χ2 = 3.13
p-value is greater than .1; do not reject the null hypothesis that the number of books sold follows
f.
a Poisson distribution.
POINTS: 1
LEARNING OBJECT BSST.ASWC.17.12.03 - Goodness of Fit Test
IVES:
NATIONAL STANDA United States - BUSPROG: Analytic
RDS:
STATE STANDARDS United States - AK - DISC: Hypothesis Testing
:
79. The number of emergency calls per day at a hospital over a period of 120 days is shown below.
Number of Observed
Emergency Calls (x) Frequency (f)
0 9
1 12
2 30
3 27
4 22
5 13
6 or more 7
Total 120
Use α = .05 and the p-value approach to see if the above data have a Poisson distribution.
ANSWER: χ2 = 4.72; p-value is greater than .1; do not reject H0; no evidence that the distribution is not
Poisson.
POINTS: 1
:
:
80. An insurance company has gathered the following information regarding the number of accidents reported per day
over a period of 100 days.
Accidents Per Day Number of Days (f )
0 5
1 18
2 25
3 24
4 20
5 or more 8
Using the critical value approach, test to see if the above data have a Poisson distribution. Let α = .05.
ANSWER: χ2 = 5.02 < 9.488; no evidence that the distribution is not Poisson.
POINTS: 1
81. A professor believes that the final examination scores in statistics are normally distributed. A sample of 40 final scores
has been taken. You are given the sample below. The mean of the scores is 83.1 and the standard deviation is 10.38.
56 63 65 68 72 72 73 75 77 78
78 79 80 80 80 80 80 80 81 81
82 84 84 86 86 87 88 90 90 92
92 93 93 94 95 96 97 98 100 100

b. Compute the test statistic for the goodness of fit test.
At the 1% level using the p-value approach, test the hypotheses. What do you conclude about the distribution of
c.
final examination scores?
ANSWER:
H0: The population of final examination scores is normally distributed with a mean of
83.1 and a standard deviation of 10.38.
a.
Ha: The population of final examination scores is not normally distributed with a mean of
83.1 and a standard deviation of 10.38
b. χ2 = 4.4
p-value is greater than .1; do not reject the null hypothesis; there is no evidence to
c.
conclude that the final examination scores are not normally distributed.
POINTS: 1
:

82. A manager believes that the shelf life of apple juice is normally distributed. A sample of 30 containers of juice was
taken and the shelf life was recorded. You are given the results below. The average shelf life in the sample was 23.07 days
with a standard deviation of 4.29 days.
15 17 19 20 20 20 21 21 21 21
21 21 21 22 22 22 22 22 22 22
24 24 25 25 27 29 30 31 32 33

b. Compute the test statistic for the goodness of fit test.
At the 5% level of significance using the p-value approach, test the hypotheses. What do you conclude about the
c.
distribution?
ANSWER:
H0: The population of the shelf life of apple juice is normally distributed with a mean of
23.07 and a standard deviation of 4.29.
a.
Ha: The population of the shelf life of apple juice is not normally distributed with a mean
of 23.07 and a standard deviation of 4.29.
b. χ2 = 12.4
c. p-value is between .005 and .01; reject the null hypothesis; the distribution is not normal.
POINTS: 1
:

83. The following data show the scores of a sample of 40 students who have taken statistics.
98 64 96 69
45 94 58 59
63 49 88 83
85 87 68 77
56 63 86 89
84 73 52 63
64 80 69 68
79 73 78 79
72 82 78 88
83 76 66 76
Use α = .10 and conduct a goodness of fit test to determine if the sample comes from a population that has a normal
distribution. Use the critical value approach.
ANSWER: χ2 = 3.2 < 9.236; the null hypothesis that the distribution is normal is not rejected.
POINTS: 1
84. We want to determine if the following sample comes from a normal distribution.
105 260 314 400 520
300 306 115 200 208
418 110 410 312 360
310 314 418 316 412
516 480 490 504 518
280 270 516 419 520
420 438 511 708 300
420 519 702 690 518
510 700 650 670 612
460 600 680 692 600
a. Compute the mean and the standard deviation.

b. Compute the test statistic. Hint: divide the distribution into 10 equal intervals.
At the 5% level of significance using the critical value approach, test to determine if the sample comes from a
c.
normal population.
d. Compute the p-value and test to see if the distribution is normal.
ANSWER: a. = 440.42
s = 163.21
b. χ2 = 23.2
c. Since the test statistic (χ2 = 23.2) is greater than = 14.067 (df = 7), the null hypothesis
is rejected, thus, concluding that the distribution is not normal.
d. p-value is less than .005; reject the null hypothesis.
POINTS: 1
:


CH 12 Comparing Multiple Proportions Test of Independence and Goodness of Fit

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

CH 12 Comparing Multiple Proportions Test of Independence and Goodness of Fit

Uploaded by

Copyright:

Available Formats

CH 12 - Comparing Multiple Proportions, Test of Independence and Goodness of Fit

1. If there are three or more populations, then it is

3. The sampling distribution for a goodness of fit test is the

4. An important application of the chi-square distribution is

Copyright Cengage Learning. Powered by Cognero. Page 2

8. The degrees of freedom for a table with 6 rows and 3 columns is

Copyright Cengage Learning. Powered by Cognero. Page 9

The calculated value for the test statistic equals

The expected frequency in the 3rd interval is

The calculated value for the test statistic equals

At the 5% level of significance, the conclusion of the test is that the

Copyright Cengage Learning. Powered by Cognero. Page 17

42. The test for goodness of fit

43. The number of categorical outcomes per trial for a multinomial probability distribution is

45. The properties of a multinomial experiment include all of the following except

Subjective Short Answer

Grocery Discount Membership

a. Provide the null and alternative hypotheses.

Emphysema Heart problem Cancer Total

a. Provide the null and alternative hypotheses.

Observed Frequencies (fi)

a. State the null and alternative hypotheses to be tested.

Illness Non-Smokers Smokers Totals

We are interested in determining whether or not illness is independent of smoking.

c. Critical chi-square = 5.991

Copyright Cengage Learning. Powered by Cognero. Page 23

a. Compute the test statistic.

Copyright Cengage Learning. Powered by Cognero. Page 24

Ha: There has been a change

We are interested in determining whether or not illness is independent of smoking.

c. Test statistic = 10.52

Copyright Cengage Learning. Powered by Cognero. Page 25

We want to determine if the position in management is independent of field (major) of concentration.

a. State the null and alternative hypotheses.

Copyright Cengage Learning. Powered by Cognero. Page 30

At α = .05, test the manufacturer's claim.

a. State the null and alternative hypotheses to be tested.

We want to determine if the selected field of study is independent of gender.

Copyright Cengage Learning. Powered by Cognero. Page 32

The results of the survey are shown below.

We want to determine if yearly income is independent of gender.

We want to see if losing weight is independent of taking the diet pills.

a. State the null and alternative hypotheses for an independence test.

Copyright Cengage Learning. Powered by Cognero. Page 36

a. What is the average number of calls during these 10-minute intervals?

a. What is the average number of books sold during a 15-minute period?

a. State the null and alternative hypotheses.

a. State the null and alternative hypotheses.

a. Compute the mean and the standard deviation.

Copyright Cengage Learning. Powered by Cognero. Page 43

You might also like