Chi-Square and Analysis of Variance (Anova)

12-1
Chapter 12
Chi-Square and
Analysis of Variance
(ANOVA)
© The McGraw-Hill Companies, Inc., 2000
12-2
Outline
 12-1 Introduction
 12-2 Test for Goodness of Fit
 12-3 Tests Using Contingency
Tables
 12-4 Analysis of Variance (ANOVA)

12-3
Objectives
 Test a distribution for goodness of fit
using chi-square.
 Test two variables for independence
using chi-square.
 Test proportions for homogeneity using
chi-square.
 Use ANOVA technique to determine a
difference among three or more means.

12-4
12-2 Test for Goodness of Fit
 When one is testing to see
whether a frequency
distribution fits a specific
pattern, the chi-square
goodness-of-fit test is used.

12-2 Test for Goodness of Fit -
12-5
Example
 Suppose a market analyst wished to see

whether consumers have any preference
among five flavors of a new fruit soda. A
sample of 100 people provided the
following data:
Cherry Straw- Orange Lime Grape
berry
32 28 16 14 10

12-6
Example
 If there were no preference, one

would expect that each flavor would
be selected with equal frequency.
 In this case, the equal frequency is
100/5 = 20.
 That is, approximately 20 people
would select each flavor.
12-7
Example
 The frequencies obtained from the

sample are called observed
frequencies.
frequencies
 The frequencies obtained from
calculations are called expected
frequencies.
frequencies
 Table for the test is shown next.
12-8
Example
Freq. Cherry Straw- Orange Lime Grape

berry
Observed 32 28 16 14 10
Expected 20 20 20 20 20

12-9
Example
 The observed frequencies will almost

always differ from the expected
frequencies due to sampling error.
 Question: Are these differences
significant, or are they due to chance?
 The chi-square goodness-of-fit test will
enable one to answer this question.

12-10
Example
 The appropriate hypotheses for this

example are:
 H0: Consumers show no preference for
flavors of the fruit soda.
 H1: Consumers show a preference.
 The d. f. for this test is equal to the
number of categories minus 1.

12-11
Formula
  
2 O  E  2
E
d . f . number of categories  1
O  observed frequency
E  expected frequency
12-12
Example
 Is there enough evidence to reject the

claim that there is no preference in the
selection of fruit soda flavors? Let
 = 0.05.
 Step 1: State the hypotheses and
identify the claim.

12-13
Example
 H0: Consumers show no preference for

flavors (claim).
 H1: Consumers show a preference.
 Step 2: Find the critical value. The d. f.
are 5 – 1 = 4 and  = 0.05. Hence, the
critical value = 9.488.

12-14
Example
 Step 3: Compute the test value.

 = (32 – 20)2/20 + (28 is – 20)2/20 + … +
(10 – 20)2/20 = 18.0.
 Step 4:Make
4: the decision. The
decision is to reject the null hypothesis,
since 18.0 > 9.488.

12-15
Example
 Step 5: Summarize the results. There is

enough evidence to reject the claim that
consumers show no preference for the
flavors.

12-16
Example

9.488

12-17
Example
 The advisor of an ecology club at a large

college believes that the group consists
of 10% freshmen, 20% sophomores, 40%
juniors, and 30% seniors. The
membership for the club this year
consisted of 14 freshmen, 19
sophomores, 51 juniors, and 16 seniors.
At  = 0.10, test the advisor’s conjecture.

12-18
Example

identify the claim.
 H0: The club consists of 10% freshmen,
20% sophomores, 40% juniors, and
30% seniors (claim)
 H1: The distribution is not the same as
stated in the null hypothesis.

12-19
Example
 Step 2: Find the critical value. The d. f.

are 4 – 1 = 3 and  = 0.10. Hence, the
critical value = 6.251.
 Step 3: Compute the test value.
 = (14 – 10)2/10 + (19 – 20)2/20 + … +
(16 – 30)2/30 = 11.208.

12-20
Example
 Step 4:Make
4: the decision. The
decision is to reject the null hypothesis,
since 11.208 > 6.251.
 Step 5: Summarize the results. There is
enough evidence to reject the advisor’s
claim.

12-21
12-3 Tests Using Contingency Tables
 When data can be tabulated in table

form in terms of frequencies, several
types of hypotheses can be tested using
the chi-square test.
 Two such tests are the independence of
variables test and the homogeneity of
proportions test.

12-22
12-3 Tests Using Contingency Tables
 The test of independence of variables is

used to determine whether two variables
are independent when a single sample is
selected.
 The test of homogeneity of proportions is
used to determine whether the proportions
for a variable are equal when several
samples are selected from different
populations.
12-3 Test for Independence -
12-23
Example
 Suppose a new postoperative procedure

is administered to a number of patients
in a large hospital.
 Question: Do the doctors feel
differently about this procedure from
the nurses, or do they feel basically the
same way?
 Data is on the next slide.
12-24
Example
Group
Group Prefer
Prefer Prefer
Prefer No
No
new
new old
old preference
preference
procedure
procedure procedure
procedure
Nurses
Nurses 100
100 80
80 20
20
Doctors
Doctors 50
50 120
120 30
30

12-25
Example
 The null and the alternative hypotheses

are as follows:
 H0: The opinion about the procedure is
independent of the profession.
 H1: The opinion about the procedure is
dependent on the profession.

12-26
Example
 If the null hypothesis is not rejected, the

test means that both professions feel
basically the same way about the
procedure, and the differences are due to
chance.
 If the null hypothesis is rejected, the test
means that one group feels differently
about the procedure from the other.

12-27
Example
 Note: The rejection of the null hypothesis

does not mean that one group favors the
procedure and the other does not.
 The test value is the 2 value (same as the
goodness-of-fit test value).
 The expected values are computed from:
(row sum)(column sum)/(grand total).

12-28
Example

12-29
Example
 From the MINITAB output, the P-

value = 0. Hence, the null hypothesis
will be rejected.
 If the critical value approach is used, the
degrees of freedom for the chi-square
critical value will be (number of
columns –1)(number of rows – 1).
 d.f. = (3 –1)(2 – 1) = 2.
12-3 Test for Homogeneity of
12-30
Proportions
 Here, samples are selected from several

different populations and one is
interested in determining whether the
proportions of elements that have a
common characteristic are the same for
each population.

12-31
Proportions
 The sample sizes are specified in

advance, making either the row totals or
column totals in the contingency table
known before the samples are selected.
 The hypotheses will be: H0:
p1 = p2 = … = pk H1: At
least one proportion is different from the
others.

12-32
Proportions
 The computations for this test

are the same as that for the test
of independence.

12-33
12-4 Analysis of Variance (ANOVA)
 When an F test is used to test a

hypothesis concerning the
means of three or more
populations, the technique is
called analysis of variance
(ANOVA).
(ANOVA)

12-4 Assumptions for the F Test for
12-34
Comparing Three or More Means
 The populations from which the

samples were obtained must be
normally or approximately normally
distributed.
 The samples must be independent of
each other.
 The variances of the populations must
be equal.

12-35
12-4 Analysis of Variance
 Although means are being compared

in this F test, variances are used in the
test instead of the means.
 Two different estimates of the
population variance are made.

12-36
 Between-group variance - this involves

computing the variance by using the
means of the groups or between the
groups.
 Within-group variance - this involves
computing the variance by using all the
data and is not affected by differences
in the means.

12-37
 The following hypotheses should be

used when testing for the difference
between three or more means.
 H0:   =  = … = k
 H1: At least one mean is different from
the others.

12-38
 d.f.N. = k – 1, where k is the number of

groups.
 d.f.D. = N – k, where N is the sum of the
sample sizes of the groups.
 Note: The formulas for this test are
tedious to work through, so examples
will be done in MINITAB. See text for
formulas.

12-39 12-4 Analysis of Variance -Example
 A marketing specialist wishes to see

whether there is a difference in the average
time a customer has to wait in a checkout
line in three large self-service department
stores. The times (in minutes) are shown on
the next slide.
 Is there a significant difference in the mean
waiting times of customers for each store
using  = 0.05?

Store
StoreAA Store
StoreBB Store
StoreCC
33 55 11
22 88 33
55 99 44
66 66 22
33 22 77
11 55 33


identify the claim.
 H0:   =  H1:
At least one mean is different from the
others (claim).

 Step 2: Find the critical value. Since

k = 3, N = 18, and  = 0.05, d.f.N. = k – 1
= 3 – 1= 2, d.f.D. = N – k = 18 – 3 = 15.
The critical value is 3.68.
 Step 3: Compute the test value. From
the MINITAB output, F = 2.70. (See
your text for computations).

 Step 4: Make a decision. Since 2.70

< 3.68, the decision is not to reject the
null hypothesis.
 Step 5: Summarize the results. There
is not enough evidence to support the
claim that there is a difference among
the means. The ANOVA summary table
is given on the next slide.


Chi-Square and Analysis of Variance (Anova)

Uploaded by

Copyright:

Available Formats

Chi-Square and Analysis of Variance (Anova)

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

Chi-Square and Analysis of Variance (Anova)

Uploaded by

Copyright:

Available Formats

12-1

© The McGraw-Hill Companies, Inc., 2000

© The McGraw-Hill Companies, Inc., 2000

© The McGraw-Hill Companies, Inc., 2000

 Suppose a market analyst wished to see

© The McGraw-Hill Companies, Inc., 2000

 If there were no preference, one

 The frequencies obtained from the

Freq. Cherry Straw- Orange Lime Grape

© The McGraw-Hill Companies, Inc., 2000

 The observed frequencies will almost

© The McGraw-Hill Companies, Inc., 2000

 The appropriate hypotheses for this

© The McGraw-Hill Companies, Inc., 2000

 Is there enough evidence to reject the

© The McGraw-Hill Companies, Inc., 2000

 H0: Consumers show no preference for

© The McGraw-Hill Companies, Inc., 2000

 Step 3: Compute the test value.

© The McGraw-Hill Companies, Inc., 2000

 Step 5: Summarize the results. There is

© The McGraw-Hill Companies, Inc., 2000

© The McGraw-Hill Companies, Inc., 2000

 The advisor of an ecology club at a large

© The McGraw-Hill Companies, Inc., 2000

 Step 1: State the hypotheses and

© The McGraw-Hill Companies, Inc., 2000

 Step 2: Find the critical value. The d. f.

© The McGraw-Hill Companies, Inc., 2000

© The McGraw-Hill Companies, Inc., 2000

 When data can be tabulated in table

© The McGraw-Hill Companies, Inc., 2000

 The test of independence of variables is

 Suppose a new postoperative procedure

© The McGraw-Hill Companies, Inc., 2000

 The null and the alternative hypotheses

© The McGraw-Hill Companies, Inc., 2000

 If the null hypothesis is not rejected, the

© The McGraw-Hill Companies, Inc., 2000

 Note: The rejection of the null hypothesis

© The McGraw-Hill Companies, Inc., 2000

© The McGraw-Hill Companies, Inc., 2000

 From the MINITAB output, the P-

 Here, samples are selected from several

© The McGraw-Hill Companies, Inc., 2000

 The sample sizes are specified in

© The McGraw-Hill Companies, Inc., 2000

 The computations for this test

© The McGraw-Hill Companies, Inc., 2000

 When an F test is used to test a

© The McGraw-Hill Companies, Inc., 2000

 The populations from which the

© The McGraw-Hill Companies, Inc., 2000

 Although means are being compared

© The McGraw-Hill Companies, Inc., 2000

 Between-group variance - this involves

© The McGraw-Hill Companies, Inc., 2000

 The following hypotheses should be

© The McGraw-Hill Companies, Inc., 2000