You are on page 1of 15

Nonparametric Methods:

Analysis of Ranked Data

Chapter 18

McGraw-Hill/Irwin Copyright © 2010 by The McGraw-Hill Companies, Inc. All rights reserved.
GOALS

1. Conduct the sign test for dependent samples using the


binomial and standard normal distributions as the test statistics.
2. Conduct a test of hypothesis for dependent samples using the
Wilcoxon signed-rank test.
3. Conduct and interpret the Wilcoxon rank-sum test for
independent samples.
4. Conduct and interpret the Kruskal-Wallis test for several
independent samples.
5. Compute and interpret Spearman’s coefficient of rank
correlation.
6. Conduct a test of hypothesis to determine whether the
correlation among the ranks in the population is different from
zero.

18-2
The Sign Test
EXAMPLE
 The Sign Test is based on the sign of a The director of information systems at Samuelson Chemicals
difference between two related recommended that an in-plant training program be instituted for
managers. The objective is to improve the knowledge of
observations. database usage in accounting, procurement, production, and so
 Assumption regarding the shape of the on. A sample of 15 managers was selected at random. A panel of
population of differences is NOT necessary. database experts determined the general level of competence of
each manager with respect to using the database. Their
 The binomial distribution is the test statistic competence and understanding were rated as being either
for small samples and the standard normal outstanding, excellent, good, fair, or poor. After the three-month
(z) for large samples. training program, the same panel of information systems experts
 The test requires dependent (related) rated each manager again. The two ratings (before and after) are
shown along with the sign of the difference. A “+” sign indicates
samples. improvement, and a “-” sign indicates that the manager’s
competence using databases had declined after the training
Procedure to conduct the test: program.
 Determine the sign (+ or -) of the difference
between pairs.
Did the in-plant training program effectively increase the competence
of the managers using the company’s database?
 Determine the number of usable pairs.
 Compare the number of positive (or
negative) differences to the critical value.
 n is the number of usable pairs (without
ties), X is the number of pluses or minuses,
and the binomial probability
 π = .5

18-3
The Sign Test –
Example

Step 1: State the Null and Alternative Hypotheses

H0: π ≤.5 (There is no increase in competence as a


result of the in-plant training program.)
H1: π >.5 (There is an increase in competence as a
result of the in-plant training program.)

Step 2: Select a level of significance.


We chose the .10 level.

Step 3: Decide on the test statistic.


It is the number of plus signs resulting from the
experiment.

Step 4: Formulate a decision rule. In this example α


is .10.
 The probability of 3 or fewer successes is .029,
found by .000 + .001 + .006 + .022.
 The probability of 11 or more successes is also .029.
Adding the two probabilities gives .058. This is the
closest we can come to .10 without exceeding it.
 Hence, the decision rule for a two-tailed test would Step 5: Make a decision regarding the null hypothesis.
be to reject the null hypothesis if there are 3 or fewer Eleven out of the 14 managers in the training course increased their
plus signs, or 11 or more plus signs.
database competency. The number 11 is in the rejection region,
.
which starts at 10, so the null hypothesis is rejected.

We conclude that the three-month training course was effective. It


increased the database competency of the managers.
18-4
Normal Approximation
 If the number of observations in the sample is larger than 10, the normal distribution can be used to
approximate the binomial.

EXAMPLE Step 3: Select the test statistic.


The market research department of Cola, Inc., has been Use Z-distribution
given the assignment of testing a new soft drink. Two where µ=.50n and σ=.50 n
versions of the drink are considered—a rather sweet drink
and a somewhat bitter one. A preference test is to be Step 4: Formulate the decision rule.
conducted consisting of a sample of 64 consumers. Each Referring to Appendix B.1, Areas under the Normal Curve,
consumer will taste both the sweet cola (labeled A) and the for a two-tailed test (because states that π ≠ .50), at the .05
bitter one (labeled B) and indicate a preference. Conduct a significance level, the critical values are -1.96 and +1.96.
test of hypothesis to determine if there is a difference in the
preference for the sweet and bitter tastes. Use the .05 Step 5: Compute z, compare the computed value with
significance level. the critical value, and make a decision regarding H0
Preference for cola A was given a “+”sign and preference
for B a “-” sign. Out of the 64 in the sample, 42 preferred the
Step 1: State the null hypothesis and the alternate
sweet taste, which is cola A. Therefore, there are 42 pluses.
hypothesis.
Since 42 is more than n/2 =64/2=32, we use:
H0: π = .50 There is no
( X  .50 )  .50n ( 42  .50 )  .50( 64 )
preference z   2.38
.50 n 0.50 64
H1: π ≠ .50 There is a preference
The computed z of 2.38 is beyond the critical value of 1.96.
Step 2: Select the level of significance. Conclusion: The null hypothesis of no difference is rejected at the .05
α = 0.05 as stated in the significance level. There is evidence of a difference in consumer
preference. That is, we conclude consumers prefer one cola over
18-5 problem
another.
Wilcoxon Signed-Rank Test for
Dependent Samples

If the assumption of normality is EXAMPLE


violated for the paired-t test, use Fricker’s is a family restaurant chain located primarily in the
southeastern part of the United States. It offers a full dinner menu,
the Wilcoxon Signed-rank test. but its specialty is chicken. Recently, Fricker, the owner and
 The test requires the ordinal scale founder, developed a new spicy flavor for the batter in which the
of measurement. chicken is cooked. Before replacing the current flavor, he wants to
conduct some tests to be sure that patrons will like the spicy flavor
 The observations must be related better. Bernie selects a random sample of 15 customers, each
or dependent. customer is given a small piece of the current chicken and asked
to rate its overall taste on a scale of 1 to 20. A value near 20
indicates the participant liked the flavor, whereas a score near 0
The steps for the test are: indicates they did not like the flavor. Next, the same 15
participants are given a sample of the new chicken with the spicier
1. Compute the differences between flavor and again asked to rate its taste on a scale of 1 to 20.
related observations. Drop The results are reported in the table below. Is it reasonable to conclude
observations with 0 difference that the spicy flavor is preferred? Use the .05 significance level.
from the sample.
2. Rank the absolute differences
from low to high.
3. Return the signs to the ranks and
sum positive and negative ranks.
4. Compare the smaller of the two
rank sums with the T value,
obtained from Appendix B.7.

18-6
Wilcoxon Signed-Rank Test for
Dependent Samples - Example

Hypothesis:
H0: There is no difference in the
ratings of the two flavors.
H1: The spicy ratings are higher.

Decision Rule:
Reject H0 if the smaller of the
rank sums is 25 or less.
Computed T = 30
Critical T = 25

Decision is not to reject the null


hypothesis.
We cannot conclude there is a
difference in the flavor ratings
between the current and the
spicy.
The smaller of the two rank sums is used as the test statistic and
referred to as T.

18-7
Wilcoxon Signed-Rank Test for Dependent
Samples - Example

 The critical values for the Wilcoxon signed-rank test


are located in Appendix B.7. A portion of that table is
shown on the table below.

18-8
Wilcoxon Rank-Sum Test for Independent
Samples

 The Wilcoxon Rank-Sum Test is used to determine if two independent samples came from the same or equal populations.
 No assumption about the shape of the population is required.
 The data must be at least ordinal scale.
 Each sample must contain at least eight observations.
 To determine the value of the test statistic W, all data values are ranked from low to high as if they were from a single
population.
 The sum of ranks for each of the two samples is determined.
 The data are ranked as if the observations were part of a single sample.
 The sum of ranks for each of the two samples is determined
 If the null hypothesis is true, then the ranks will be about evenly distributed between the two samples, and the sum of the
ranks for the two samples will be about the same.

18-9
Wilcoxon Rank-Sum Test for Independent
Samples - Example

Dan Thompson, the president of CEO Set up Hypothesis and Decision Rule:
Airlines, recently noted an Hypothesis:
increase in the number of no- H0: The population distribution of no-shows is the same or
shows for flights out of Atlanta. less for Atlanta and Chicago.
He is particularly interested in H1: The population distribution of no-shows is larger for
determining whether there are Atlanta than for Chicago.
more no-shows for flights that Decision Rule: Reject H0 if: computed Z > critical Z
originate from Atlanta compared .05 level of significance = 1.65 critical Z
with flights leaving Chicago. A
sample of nine flights from
Atlanta and eight from Chicago Rank the observations from both samples as if they were a single
are reported on table. group.
At the .05 significance level, can we
conclude that there are more no-
shows for the flights originating
in Atlanta?

The Chicago flight with only 8 no-shows had the fewest, so it is assigned
a rank of 1. The Chicago flight with 9 no-shows is ranked 2, and so on.

18-10
Wilcoxon Rank-Sum Test for Independent
Samples - Example

The value of W is calculated for the Atlanta group and is found to be 96.5, which is the sum of the ranks for the
no-shows for the Atlanta flights.

The computed z value (1.49) is less than 1.65, the null hypothesis is not
rejected. It appears that the number of no-shows is the same in Atlanta as in Chicago.

18-11
Kruskal-Wallis Test:
Analysis of Variance by Ranks

EXAMPLE
A management seminar consists of executives from manufacturing, finance,
This is used to compare three or more samples to determine if they came
from equal populations.
and engineering. Before scheduling the seminar sessions, the seminar
leader is interested in whether the three groups are equally
 The ordinal scale of measurement is required.
 It is an alternative to the one-way ANOVA. knowledgeable about management principles. Plans are to take samples


The chi-square distribution is the test statistic.
Each sample should have at least five observations.
of the executives in manufacturing, in finance, and in engineering and to
 The sample data is ranked from low to high as if it were a single administer a test to each executive. If there is no difference in the scores
group.
for the three distributions, the seminar leader will conduct just one
session. However, if there is a difference in the scores, separate
sessions will be given. We will use the Kruskal-Wallis test instead of
ANOVA because the seminar leader is unwilling to assume that (1) the
populations of management scores follow the normal distribution or (2)
the population standard deviations are the same.

Step 1: Set up the Null and Alternate Hypotheses


H0: The population distributions of the management scores for the
populations of executives in manufacturing, finance, and engineering
are the same.
H1: The population distributions of the management scores for the
populations of executives in manufacturing, finance, and engineering
are NOT the same.

Step 2: State the Decision Rule


H0 is rejected if the computed H statistic is greater than critical χ2 value
of 5.991 (There are 2 degrees of freedom at the .05 significance level.)

18-12
Kruskal-Wallis Test:
Analysis of Variance by Ranks - Example

Step 3: Collect Data and Compute the Chisquare Statistic


Considering the scores as a single population, the engineering executive with a score of 35 is the lowest, so it
is ranked 1. There are two scores of 38. To resolve this tie, each score is given a rank of 2.5, found by
(2+3)/2. This process is continued for all scores.
The scores, the ranks, and the sum of the ranks for each of the three samples are given in the table below.

Because the computed value of H


(5.736) is less than the critical
value of 5.991, the null
hypothesis is not rejected.

There is not enough evidence to


conclude there is a difference
among the executives from
manufacturing, finance, and
engineering with respect to their
typical knowledge of
management principles.
18-13
Rank-Order Correlation
EXAMPLE
Spearman’s coefficient of rank
Lorrenger Plastics, Inc., recruits management trainees
correlation reports the association at colleges and universities throughout the
between two sets of ranked United States. Each trainee is given a rating by
observations. The features are: the recruiter during the on-campus interview.
This rating is an expression of future potential
and may range from 0 to 15, with the higher
 It can range from –1.00 up to 1.00. score indicating more potential. The recent
college graduate then enters an in-plant training
program and is given another composite rating
 It is similar to Pearson’s based on tests, opinions of group leaders,
coefficient of correlation, but is training officers, and so on. The on-campus
based on ranked data. rating and the in-plant training ratings are given
in the table on the right.
 It computed using the formula:

18-14
Rank-Order Correlation - Example

Conclusion:

The value of .726 indicates a strong positive association between the ratings of the on-campus recruiter and the
ratings of the training staff.

The graduates that received high ratings from the on-campus recruiter also tended to be the ones that received high
ratings from the training staff.
18-15

You might also like