Non Parametric Tests

Overview
Parametric tests have requirements
about the nature or shape of the
populations involved.
Nonparametric tests do not require
that samples come from populations
with normal distributions or have
any other particular distributions.
Consequently, nonparametric
tests are called distribution-free
tests.
Slide 2
 Advantages of Nonparametric Methods
1. Nonparametric methods can be applied to a wide
variety of situations because they do not have the more
rigid requirements of the corresponding parametric
methods. In particular, nonparametric methods do not
require normally distributed populations.

2. Unlike parametric methods, nonparametric methods can

often be applied to categorical data, such as the
genders of survey respondents.

3. Nonparametric methods usually involve simpler

computations than the corresponding parametric
methods and are therefore easier to understand and
apply.
Slide 3
 Disadvantages of
Nonparametric Methods

1. Nonparametric methods tend to waste information

because exact numerical data are often reduced to a
qualitative form.

2. Nonparametric tests are not as efficient as parametric

tests, so with a nonparametric test we generally
need stronger evidence (such as a larger sample or
greater differences) before we reject a null
hypothesis.

Slide 4
 Definitions

Data are sorted when they are arranged

according to some criterion, such as smallest
to the largest or best to worst.
A rank is a number assigned to an individual
sample item according to its order in
the sorted list. The first item is
assigned a rank of 1, the second is
assigned a rank
of 2, and so on.

Slide 6
 Handling Ties in Ranks
Find the mean of the ranks involved and assign
this mean rank to each of the tied items.
Sorted Data Preliminary Ranking Rank
4 1 1
5 2 3
2 
5 33  Mean is 3
3.
5 4  3
10 5 5
11 6 6
12  7.5
7 
 □ Mean is
12 7.5. 8  7.5
 

Slide 7
Sign Test
 Key Concept

The main objective of this test is to

understand the sign test procedure,
which involves converting data values
to plus and minus signs, then testing for
disproportionately more of either sign.

Slide 9
 Definition
Sign Test
The sign test is a nonparametric (distribution
free) test that uses plus and minus signs to test
different claims, including:

1) Claims involving matched pairs of sample data;

2) Claims involving nominal data;

3) Claims about the median of a single population.

Slide 10
 Basic Concept of the
Sign Test

The basic idea underlying the sign

test is to analyze the frequencies of
the plus and minus signs to
determine whether they are
significantly different.

Slide 11
Figure 13-1 Sign Test Procedure

Slide 12
Figure 13-1 Sign Test Procedure

Slide 13
Figure 13-1 Sign Test Procedure

Slide 14
 Requirements

1. The sample data have been

randomly selected.

2. There is no requirement that the

sample data come from a population
with a particular distribution, such
as a normal distribution.

Slide 15
 Notation for Sign Test

x = the number
of times the less
frequent sign occurs

n = the total
number of positive
and negative signs
combined

Slide 16
 Test Statistic
For n  x (the number of times the
25: less frequent sign occurs)
n
(x + 0.5) – 2
For n > z =
n
25:
2
Critical values
For n  25, critical x values are in Table A-7.

For n > 25, critical z values are in Table A-2.

Slide 17
 Claims Involving Matched Pairs
When using the sign test with data that are
matched pairs, we convert the raw data to
plus and minus signs as follows:

1. Subtract each value of the second variable

from the corresponding value of the first
variable.
2. Record only the sign of the difference found
in step 1.
Exclude ties: that is, any matched pairs in
which both values are equal.
Slide 18
Key Concept Underlying This
Use of the Sign Test

If the two sets of data have equal

medians, the number of positive
signs should be approximately equal to
the number of negative signs.

Slide 19
 Example: Yields of Corn
from Different Seeds
Use the data in with a 0.05 significance level to test
the claim that there is no difference between the
yields from the regular and kiln-dried seed.

Slide 20
 Example: Yields of Corn
from Different Seeds
Use the data with a 0.05 significance level to test the
claim that there is no difference between the yields
from the regular and kiln-dried seed.

H0: The median of the differences is equal to 0.

H1: The median of the differences is not equal to 0.
 = 0.05
x = minimum(7, 4) = 4 (From Table 13-3, there
are 7 negative signs and 4 positive signs.)
Critical value = 1 (From Table where n = 11
and  = 0.05)
Slide 21
 Example: Yields of Corn
from Different Seeds
Use the data in Table 13-3 with a 0.05 significance level
to test the claim that there is no difference between
the yields from the regular and kiln-dried seed.

H0: The median of the differences is equal to 0.

H1: The median of the differences is not equal to 0.
With a test statistic of x = 4 and a critical value of 1,
we fail to reject the null hypothesis of no difference.
There is not sufficient evidence to warrant rejection
of the claim that the median of the differences
is equal to 0.
Slide 23
 Claims Involving
Nominal Data

The nature of nominal data limits the

calculations that are possible, but we can
identify the proportion of the sample
data that belong to a particular category.

Then we can test claims about the

corresponding population proportion p.

Slide 24
 Example: Gender Selection
Of the 325 babies born to parents using the XSORT
method of gender selection, 295 were girls. Use the
sign test and a 0.05 significance level to test the claim
that this method of gender selection has no effect.

The procedures are for cases in which n > 25.

Note that the only requirement is that the sample data are
randomly selected.

H0: p = 0.5 (the proportion of girls is 0.5)

H1: p  0.5

Slide 25
 Example: Gender Selection
Of the 325 babies born to parents using the XSORT
method of gender selection, 295 were girls. Use the
sign test and a 0.05 significance level to test the claim
that this method of gender selection has no effect.

Denoting girls by the positive sign (+) and boys by the

negative sign (–), we have 295 positive signs and 30
negative signs.
Test statistic x = minimum(295, 30) = 30
The test involves two tails.

Slide 26
 Example: Gender Selection
Of the 325 babies born to parents using the XSORT
method of gender selection, 295 were girls. Use the
sign test and a 0.05 significance level to test the claim
that this method of gender selection has no effect.

n
(x + 0.5) – 2
z=
n
2
325

z= (30 + 0.5) – 2 = –14.64

325
2
Slide 27
 Example: Gender Selection
Of the 325 babies born to parents using the XSORT
method of gender selection, 295 were girls. Use the
sign test and a 0.05 significance level to test the claim
that this method of gender selection has no effect.

With  = 0.05 in a two-tailed test, the critical values

are z =  1.96.

The test statistic z = -14.64 is less than -1.96.

We reject the null hypothesis that p = 0.5.

There is sufficient evidence to warrant rejection of the
claim that the method of gender selection has no
effect.
Slide 28
 Example: Gender Selection
Of the 325 babies born to parents using the XSORT
method of gender selection, 295 were girls. Use the
sign test and a 0.05 significance level to test the claim
that this method of gender selection has no effect.

Figure 13.2

Slide 29
Claims About the Median
of a Single Population

The negative and positive signs

are based on the claimed value
of the median.

Slide 30
Example:
Consider a clinical investigation to assess the effectiveness of a new
drug designed to reduce repetitive behaviors in children affected with
autism. If the drug is effective, children will exhibit fewer repetitive
behaviors on treatment as compared to when they are untreated. A
total of 8 children with autism enroll in the study. Each child is
observed by the study psychologist for a period of 3 hours both
before treatment and then again after taking the new drug for 1 week.
The time that each child is engaged in repetitive behavior during each
3 hour observation period is measured. Repetitive behavior is scored
on a scale of 0 to 100 and scores represent the percent of the
observation time in which the child is engaged in repetitive behavior.
For example, a score of 0 indicates that during the entire observation
period the child did not engage in repetitive behavior while a score of
100 indicates that the child was constantly engaged in repetitive
behavior. The data are shown below.

Slide 31
Slide 32
If the null hypothesis is true (i.e., if the median difference is zero)
then we expect to see approximately half of the differences as
positive and half zof the differences as negative. If the research
hypothesis is true, we expect to see more positive differences.

In this example, we observe 2 negative and 6 positive signs

Slide 33
To determine the appropriate critical value we need the sample size,
which is equal to the number of matched pairs (n=8) and our one-sided
level of significance α=0.05. For this example, the critical value is 1,
and the decision rule is to reject H0 if the smaller of the number of
positive or negative signs < 1. We do not reject H0 because 2 > 1. We
do not have sufficient evidence at α=0.05 to show that there is
improvement in repetitive behavior after taking the drug as compared
to before. In essence, we could use the critical value to decide whether
to reject the null hypothesis.
 Recap

Sign tests where data are assigned plus or minus signs

and then tested to see if the number of plus and minus
signs is equal.

Sign tests can be performed on claims involving:

Matched pairs
Nominal data
The median of a single population

Slide 35
 McNemar test
What is the use of McNemar test?
In statistics, McNemar's test is a statistical test used on paired nominal
data. It is applied to 2 × 2 contingency tables with a dichotomous trait, with
matched pairs of subjects, to determine whether the row and column
marginal frequencies are equal (that is, whether there is "marginal
homogeneity").
McNemer test is utilized for two related examples as a part of
circumstances where the states of mind of individuals are noted previously,
then after the fact treatment to test the essentialness of progress in
sentiment if any.
The Mc Nemer test is especially helpful when the information speaks the
truth two related samples. For the most part this information is utilized as a
part of circumstances where the states of mind of individuals are noted
before overseeing the treatment and are then contrasted and investigations
in the wake of managing the treatment. It can along these lines be said that
utilizing McNemer test we can judge if there is any adjustment in the
demeanors or supposition of individuals subsequent to regulating the
treatment with the utilization of table as demonstrated as follows: Slide 36
Slide 37
Slide 38
Slide 39
Slide 40
=

=121/14
=8.6424

Slide 41
=

=121/14
=19.53

Slide 42
 Wilcoxon Signed-Ranks
Test for Matched
Pairs

SSliddee 38
Copyright © 2007 Pearson Education, Inc Publishing as Pearson Addison-Wesley.
 Key Concept

The Wilcoxon signed-ranks test uses ranks of

sample data consisting of matched pairs.
This test is used with a null hypothesis that the
population of differences from the matched pairs
has a median equal to zero.
 Definition
The Wilcoxon signed-ranks test is a
nonparametric test that uses ranks of sample
data consisting of matched pairs.
It is used to test the null hypothesis that the
population of differences has a median of zero.

H0 : The matched pairs have differences

that come from a population with a
median equal to zero.
H1 : The matched pairs have differences that
come from a population with a nonzero
median.
 Wilcoxon Signed-Ranks Test
Requirements
1.The data consist of matched pairs that have
been randomly selected.
2.The population of differences (found from the
pairs of data) has a distribution that is
approximately symmetric, meaning that the left
half of its histogram is roughly a mirror image of
its right half. (There is no requirement that the
data have a normal distribution.)
 Notation
T = the smaller of the following two
sums:
1. The sum of the absolute values
of the negative ranks of the nonzero
differences d
2. The sum of the positive ranks of
the nonzero differences d
 Test Statistic for the Wilcoxon
Signed-Ranks Test for
Matched Pairs

For n  30, the test statistic is T.

For n > 30, the test statistic is z T – n(n + 1)

4
=
n(n +1) (2n +1)
24
 Critical Values for the
Wilcoxon Signed-Ranks Test
for Matched Pairs

For n  30, the critical T value is found in

t table value.

For n > 30, the critical z values are found in

z table value.
 Procedure for Finding the
Value of the Test Statistic
Step 1: For each pair of data, find the difference d by subtracting the
second value from the first. Keep the signs, but discard any
pairs for which d = 0.

Step 2: Ignore the signs of the differences, then sort the

differences from lowest to highest and replace the
differences by the corresponding rank value. When
differences have the same numerical value, assign to them
the mean of the ranks involved in the tie.

Step 3: Attach to each rank the sign difference from which it came.
That is, insert those signs that were ignored in step 2.

Step 4: Find the sum of the absolute values of the negative ranks.
Also find the sum of the positive ranks.
 Procedure for Finding the
Value of the Test Statistic

Step 5: Let T be the smaller of the two sums found in Step 4.

Either sum could be used, but for a simplified procedure
we arbitrarily select the smaller of the two sums.

Step 6: Let n be the number of pairs of data for

which the difference d is not 0.

Step 7: Determine the test statistic and critical values based

on the sample size, as shown above.

Step 8: When forming the conclusion, reject the null

hypothesis if the sample data lead to a test statistic that is
in the critical region - that is, the test statistic is less than
or equal to the critical value(s). Otherwise, fail to reject
the null hypothesis.
 Example: Does the Type of Seed
Affect Corn Growth?
Use the data in Table 13-4 with the Wilcoxon signed-ranks
test and 0.05 significance level to test the claim that
there is no difference between the yields from the regular
and kiln-dried seed.
 Example: Does the Type of Seed
Affect Corn Growth?
Use the data in Table 13-4 with the Wilcoxon signed-ranks
test and 0.05 significance level to test the claim that
there is no difference between the yields from the regular
and kiln-dried seed.

H0 : There is no difference between the times

of the first and second trials.
H1 : There is a difference between the times
of the first and second trials.
 Example: Does the Type of Seed
Affect Corn Growth?
 The ranks of differences in row four of the
table are found by ranking the absolute
differences, handling ties by assigning the
mean of the ranks.

 The signed ranks in row five of the table are

found by attaching the sign of the differences
to the ranks.
 The differences in row three of the table are
found by computing the first time – second
time.
 Example: Does the Type of Seed
Affect Corn Growth?
Calculate the Test Statistic
Step 1: In Table 13- 4, the row of differences
is obtained by computing this difference
for each pair of data:
d = yield from regular seed – yield from kiln- dried
seed
Step 2: Ignoring their signs, we rank the
absolute differences from lowest to highest.
Step 3: The bottom row of Table is created by
attaching to each rank the sign of the
corresponding differences.
 Example: Does the Type of Seed
Affect Corn Growth?
Calculate the Test Statistic

Step 3 (cont.): If there really is no difference

between the yields from the two types of
seed (as in the null hypothesis), we expect
the sum of the positive ranks to be
approximately equal to the sum of the
absolute values of the negative ranks.
Step 4: We now find the sum of the absolute
values of the negative ranks, and we also find
the sum of the positive ranks.
 Example: Does the Type of Seed
Affect Corn Growth?
Calculate the Test Statistic
Step 4 (cont.):
Sum of absolute values of negative ranks: 51
(from 10 + 9 + 8 + 6 + 5 + 11 + 2)
Sum of positive ranks: 15 (from 1 + 3 + 4 + 7)
Step 5: Letting T be the smaller of the two
sums found in Step 4, we find that T = 15.
Step 6: Letting n be the number of pairs of data
for which the difference d is not 0, we have
n = 11.
 Example: Does the Type of Seed
Affect Corn Growth?
Calculate the Test Statistic
Step 7: Because n = 11, we have n ≤ 30, so we
use a test statistic of T = 15. From Table, the
critical T = 11 (using n = 11 and  = 0.05 in
two tails).
Step 8: The test statistic T = 15 is not less than
or equal to the critical value of 11, so we fail
to reject the null hypothesis.
It appears that there is no difference between
yields from regular seed and kiln-dried seed.
 Recap

In this section we have discussed:

The Wilcoxon signed-ranks test which

uses matched pairs.

The hypothesis is that the matched

pairs have differences that come from a
population with a median equal to
zero.
 Wilcoxon Rank-Sum Test
for Two Independent Sample
or Mann Whitney U test
 Key Concept

The Wilcoxon signed-ranks test

involves matched pairs of
data.
The Wilcoxon rank-sum test of this
section involves two independent
samples that are not related or
somehow matched or paired.
 Definition
The Wilcoxon rank-sum test is a nonparametric
test that uses ranks of sample data from two
independent populations. It is used to test the
null hypothesis that the two independent
samples come from populations with equal
medians.

H0 : The two samples come from

populations with equal medians.
H1 : The two samples come from
populations with different medians.
 Basic Concept

If two samples are drawn from

identical populations and the
individual values are all ranked as
one combined collection of values,
then the high and low ranks should
fall evenly between the two samples.
 Requirements

1. There are two independent samples of

randomly selected data.

2. Each of the two samples has more than 10

values.

3. There is no requirement that the two

populations have a normal distribution or
any other particular distribution.
 Notation for the
Wilcoxon Rank-Sum Test
n1 = size of Sample 1
n2 = size of Sample 2
R1 = sum of ranks for Sample 1
R2 = sum of ranks for Sample 2
R = same as R1 (sum of ranks for Sample 1)
R = mean of the sample R values that is
when the two populations have equal medians
expected
R = standard deviation of the sample R values that
is expected with two populations having
equal medians
 Test Statistic for the
Wilcoxon Rank-Sum Test
R – R
z  R
=
n1 (n1 + n2 + 1)
where  R
=
2

R = n1 n2 (n1 + n2
+ 1) 12
n1 = size of the sample from which the
rank sum R is found
n2 = size of the other sample
R = sum of ranks of the sample with size n1
 Critical Values for the
Wilcoxon Rank-Sum Test

Critical values can be found in Table z

table (because the test statistic is
based on the normal distribution).
 Procedure for Finding the
Value of the Test
Statistic
1. Temporarily combine the two samples
into one big sample, then replace each
sample value with its rank.

2. Find the sum of the ranks for either one

of the two samples.

3. Calculate the value of the z test statistic

as shown in the previous slide, where
either sample can be used as ‘Sample 1’.
 Example:
BMI of Men and Women
The data in Table are from
Data Set and in which first 13
sample values for men and
the first 12 sample values for
women.

The numbers in parentheses

are their ranks beginning with
a rank of 1 assigned to the
lowest value of 17.7.

R1 and R2 at the bottom denote

the sum of ranks.
 Example:
BMI of Men and Women
Use the data in Table with the Wilcoxon rank-sum test
and a 0.05 significance level to test the claim that the
median BMI of men is equal to the median BMI of
women.
The requirements of having two independent and
random samples and each having more than 10 values
are met.

H0: Men and women have BMI values with equal

medians
H1: Men and women have BMI values with medians that
are not equal
 Example:
BMI of Men and Women
Use the data in Table with the Wilcoxon rank-sum test
and a 0.05 significance level to test the claim that the
median BMI of men is equal to the median BMI of
women.
Procedures
1.Rank all 25 BMI measurements combined.
2.Find the sum of the ranks of either one of
the samples. For men the sum of ranks is
R = 11.5 + 9 + 14 + … + 15.5 = 187
 Example:
BMI of Men and Women
Procedures (cont.)
3. Calculate the value of the z test statistic.

R  n1 (n1  n2 1)  13(13 12 1) 

2 2
169
 R  n1n2 (n1  n2 1)  (13)(12)(13 12 1) 
12 12
18.385
R  R 187 169
z  18.385  0.98
R
 Example:
BMI of Men and Women
Use the data in Table with the Wilcoxon rank-sum test
and a 0.05 significance level to test the claim that the
median BMI of men is equal to the median BMI of
women.

A large positive value of z would indicate that

the higher ranks are found disproportionately in
Sample 1, and a large negative value of z would
indicate that Sample 1 had a disproportionate
share of lower ranks.
 Example:
BMI of Men and Women
Use the data in Table with the Wilcoxon rank-sum test
and a 0.05 significance level to test the claim that the
median BMI of men is equal to the median BMI of
women.
We have a two tailed test (with  = 0.05), so the
critical values are 1.96 and –1.96.
The test statistic of 0.98 does not fall within the
critical region, so we fail to reject the null hypothesis
that men and women have BMI values with equal
medians.
It appears that BMI values of men and women are
basically the same.
 Recap

In this section we have discussed:

The Wilcoxon Rank-Sum Test for Two

Independent Samples.

It is used to test the null hypothesis that

the two independent samples come from
populations with equal medians.
 MANN-WHITNEY U TEST

 This non-parametric test for two samples was described by

Wilcoxon and studied by Mann and Whitney.
 The Mann-Whitney U test is used to compare difference
between two independent groups when the dependent variable
is either ordinal or continuous, but not normally distributed.

 It is most widely used test as an (parametric).

 It works on interval and ordinal data.
 It can be used for very small samples.
 Alternative to independent sample t test
 MANN-WHITNEY U TEST (TEST P R O C E D U R E )

 The test statistic of Mann-Whitney U test is as follows:

U 1 = w 1 – n1 (n1 + 1)/2
U 2 = w 2 - n2(n2+1))/2
Where,
w1 and w2 are the total ranks for group 1 and 2,
n 1 & n 2 are the independent ordered samples of size n 1
and n 2 respectively.

 The test statistic for the value of U is the minimum of U 1 and U 2 , and

compare with critical values of U 1 and U 2 for level of significance (say, 0.05).

 If the minimum value of U 1 or U 2 is less than or equal to table critical value,

the null hypothesis is rejected (Significant) other wise it is accepted

(Not significant) at the level of significance.

 MANN-WHITNEY U TEST (TEST P R O C E D U R E )

 The test statistic of Mann-Whitney U test is as follows:

U = n 1 n 2 + (n2(n2+1))/2 – T
Where,
n1 & n2 are the independent ordered samples of size n 1 and n2
respectively, T is the sum of ranks of the second group in the
combined ordered sample.

Consequently, the null hypothesis (H0) is rejected, if U ≤ critical

value, other wise
accept H 0 .

 If T is significantly large or small then then null hypothesis

is rejected. Z = (U – n 1n 2/2) / (for large sample, say, n 1 & n 2 > 20)

√n1n 2(n 1+n 2+1)/12

 The Mann-Whitney U test is always superior to the t-test for decidedly

non-normal populations.
M A N N -W H I T N E Y U T E S T Mann-Whitney U test
(PROBLEM) A B Rank A Rank B
63 75 1 5
69 88 4 10
78 64 6 2
91 82 11 9
80 93 8 12
79 7
67 3
5 7 30 48

H0: Median(A) = Median (B)

U 1 = w 1 – n1 (n1 + 1)/2
w1 30
w2 48
U 2 = w 2 - n2(n2+1))/2
U1 15
U stat = min (U 1 , U 2 ) U2 20
U stat 15
Critical Region (5,7) at alpha 0.05 is 5 (table value)

Decision:- Ustat > 5 15 > 5

Accept H0
The Friedman Fr Test
 The Friedman Fr Test
 This test is similar to a oneway repeated measures ANOVA,
however, the data on the dependent variable is measured on an
ordinal scale.
 The test assumes the study involves one independent variable, and
that the same participants are repeatedly observed under three or
more conditions.
 Also, the present test bears some resemblance to the Wilcoxon
matched pairs signed rank test. However, the Wilcoxon involves
one independent variable with two and only two levels and the
participants in the study are in both conditions.
 The present test also involves only one independent variable with
the same participants in three or more conditions of the study, and
a dependent variable measured on an ordinal scale.
 • The Friedman Fr Test is the nonparametric
equivalent of the randomized block design
with k treatments and b blocks.
• All k measurements within a block are ranked
from 1 to b.
• We use the sums of the ranks of the k treatment
observations to compare theblock
k treatment
Rank the k measurements within each block from 1 to k. Tied
Rank the k measurements within each from 1 to k. Tied
observations
observations are
are assigned
assigned average
average of
of the
the ranks
ranks they
they would
would have
have gotten
gotten ifif
distributions.
not
not tied.
tied.
Calculate
Calculate
 T
Ti i == rank
rank sum
sum for
forthe
the ith
ith treatment
treatment ii == 1, 1, 2,…,k
2,…,k
and the test statistic
and the test statistic 12
Fr   Ti 2  3b(k  1)
bk (k  1)
 The Friedman Fr Test

H
H00:: the
the kk treatments
treatments are
are identical
identical versus
versus
H
Haa:: at
at least
least one
one distribution
distribution isis different
different
Test
Test statistic:
statistic: Friedman
Friedman FFrr
When
When H H00 isis true,
true, the
the test
test statistic
statistic FFrr has
has an
an
approximate
approximate chi-square
chi-square distribution
distribution withwith df
df
== k-1.
k-1.
Use
Use aa right-tailed
right-tailed rejection
rejection region
region oror p-
p-
value
value based
based on on the
the Chi-square
Chi-square distribution.
distribution.
 Example
A student is subjected to a stimulus and we measure the time
until the student reacts by pressing a button. Four students
are used in the experiment, each is subjected to three stimuli,
and their reaction times are measured. Do the distributions
of reaction times differ for the three stimuli?
Stimuli Rank
Rankthe
the33measurements
measurementsfor for
Subject 1 2 3 each
eachsubject
subjectfrom
from11to to3,
3,and
and
1 .6 .9 .8
calculate
calculatethe
thethree
threerank
ranksums.
sums.
2 .7 1.1 .7
3 .9 1.3 1.0
HH00::the
thedistributions
distributionsof
ofreaction
reactiontimes
times
4 .5 .7 .8
are
arethethesame
same
HHaa::the
thedistributions
distributionsdiffer
differin
intime
time
 Stimuli
Subject 1 2 3
1 .6 (1) .9 (3) .8 (2)
2 .7 (1.5) 1.1 (3) .7(1.5)
3 .9 (1) 1.3 (3) 1.0 (2)
4 .5 (1) .7 (2) .8 (3)

Ti 4.5 11 8.5

12
Test statistic : Fr   Ti 2  3b(k  1)
bk (k  1)
12
 (4.52  112  8.52 )  3(4)(4)  5.375
12(4)

Rejection
Rejectionregion:
region:Use UseTable.
Table.For
Foraaright-
right- DoDonot
notreject
rejectHH0.0.There
Thereisisinsufficient
insufficient
tailed
tailedchi-square
chi-squaretest
testwith
withaa==.05
.05and
anddfdf== evidence
evidencetotoindicate
indicatethat
thatthere
thereisisaadifference
difference
3-1
3-1=2, rejectHH00ififHH 5.99.
=2,reject 5.99. ininreaction
reactiontimes
timesforforthe
thethree
threestimuli.
stimuli.
Kruskal-Wallis Test
 Key Concept

This section introduces the Kruskal-

Wallis test, which uses ranks of
data from three or more
independent samples to test the
null hypothesis that the samples
come from populations with equal
medians.
 Kruskal-Wallis Test
Definition
• The Kruskal-Wallis test (also called the H
test) is a nonparametric test that uses ranks
of sample data from three or more
independent populations.
• It is used to test the null hypothesis that the
independent samples come from populations
with the equal medians.
H0 : The samples come from populations
with equal medians.
H1: The samples come from populations with
medians that are not all equal.
 Kruskal-Wallis Test

• We compute the test statistic H, which has a

distribution that can be approximated by
the chi-square (2 ) distribution as long as
each sample has at least 5 observations.

• When we use the chi-square distribution in

this context, the number of degrees of
freedom is k – 1, where k is the number of
samples.
 Kruskal-Wallis Test
Requirements
1. We have at least three independent
samples, all of which are randomly
selected.

2. Each sample has at least 5

observations.

3. There is no requirement that the

populations have a normal distribution or
any other particular distribution.
 Kruskal-Wallis Test
Notation
• N = total number of observations in
all observations combined
• k = number of samples
• R1 = sum of ranks for Sample 1
• n1 = number of observations in
Sample 1
• For Sample 2, the sum of ranks is R2 and the
number of observations is n2 , and similar
notation is used for the other samples.
 Kruskal-Wallis Test
Test Statistic
12 □ 1  R2
R 
2
H 2
 ... k  3(N
□ 
N (N 1) R 2n1  n2  1)
nk Critical Values
1. Test is right-tailed.
2. df = k – 1 (Because the test statistic H can
be approximated by the 2 distribution, use
Table chi square table).
 Procedure for Finding the Value
of the Test Statistic H
1 Temporarily combine all samples into one
big sample and assign a rank to each
sample value.
2. For each sample, find the sum of the ranks
and find the sample size.
3. Calculate H by using the results of Step 2 and
the notation and test statistic given on the
preceding slide.
 Procedure for Finding the Value
of the Test Statistic H
The test statistic H is basically a measure of
the variance of the rank sums R1 , R2 , … , R k.
If the ranks are distributed evenly among the
sample groups, then H should be a
relatively small number.
If the samples are very different, then the
ranks will be excessively low in some groups
and high in others, with the net effect that H
will be large.
 Example: Effects of Treatments
on Poplar Tree Weights
Table lists weights of poplar trees given
different treatments. (Numbers in parentheses
are ranks.)
 Example: Effects of Treatments
on Poplar Tree Weights
Use the data in Table with the Kruskal-Wallis test to
test the claim that the four samples come from
populations with equal medians.
Are requirements met?
There are three or more independent and random
samples.
Each sample size is 5. (Requirement is at least
5.)

H0: The populations of poplar tree weights from the four

treatments have equal medians.
H1: The four population medians are not all equal.
 Example: Effects of Treatments
on Poplar Tree Weights
Use the data in Table with the Kruskal-Wallis test to
test the claim that the four samples come from
populations with equal medians.

The following statistics come from Table :

n1 = 5, n2 = 5, n3 = 5, n4 = 5
N = 20
R1 = 45, R2 = 37.5, R3 = 42.5, R4
= 85
 Example: Effects of Treatments
on Poplar Tree Weights
Use the data in Table with the Kruskal-Wallis test to
test the claim that the four samples come from
populations with equal medians.

Evaluate the test statistic.

12 □ 2 2 2

H R

R
 
R
...   3(N
1 2 k
□
N (N 1)  n1 n2 nk
1)
 12  45 2
37.5 2
42.5 2
85 2
 3(20
20(20 1) 5  5   
5 5  1)
 

8.214
 Example: Effects of Treatments
on Poplar Tree Weights
Use the data in Table with the Kruskal-Wallis test to
test the claim that the four samples come from
populations with equal medians.

Find the critical value.

Because each sample has at least five observations,
the distribution of H is approximately a chi-square
distribution.

df = k–1 = 4–1 = 3 α = 0.05

From Table the critical value = 7.815.
 Example: Effects of Treatments
on Poplar Tree Weights
Use the data in Table with the Kruskal-Wallis test to
test the claim that the four samples come from
populations with equal medians.

The test statistic 8.214 is in the critical region, so we

reject the null hypothesis of equal medians.

At least one of the medians appears to be different

from the others.
 Recap
In this section we have discussed:

The Kruskal-Wallis Test is the non-

parametric equivalent of ANOVA.

It tests the hypothesis that three or

more populations have equal means.

The populations do not have to be

normally distributed.
 Rank Correlation

SSliddee 90
Copyright © 2007 Pearson Education, Inc Publishing as Pearson Addison-Wesley.
 Key Concept

This section describes the nonparametric method of

rank correlation, which uses paired data to test for
an association between two variables.

In correlation chapter we used paired sample data to

compute values for the linear correlation coefficient
r, but in this section we use ranks as a the basis for
computing the rank correlation coefficient rs .
 Rank Correlation
Definition
The rank correlation test (or Spearman’s rank
correlation test) is a non-parametric test that uses
ranks of sample data consisting of matched
pairs.

It is used to test for an association between two

variables, so the null and alternative hypotheses are
as follows (where ρs denotes the rank correlation
coefficient for the entire population):
H o : ρs = 0 (There is no correlation between
the two variables.)
H 1 : ρs  0 (There is a correlation between
the two variables.)
 Advantages
1. The nonparametric method of rank
correlation can be used in a wider variety of
circumstances than the parametric method of
linear correlation. With rank correlation,
we can analyze paired data that are ranks or
can be converted to ranks.
2. Rank correlation can be used to detect some
(not all) relationships that are not linear.
 Requirements

1. The sample paired data have been

randomly selected.
2. Unlike the parametric method there is
no requirement that the sample pairs
of data have a bivariate normal
distribution. There is no requirement
of a normal distribution for any
population.
 Notation
rs = rank correlation coefficient for sample
paired data (rs is a sample statistic)
s = rank correlation coefficient for all the population
data (s is a population parameter)

n = number of pairs of data

d = difference between ranks for the two

values within a pair
 Rank Correlation
Test Statistic
No ties: After converting the data in each sample to ranks, if
there are no ties among ranks for either variable, the exact
value of the test statistic can be calculated using this formula:
6d 2
rs  1
n(n 2 1
Repeated ranks )
When two or more items have equal values (i.e., a tie) it is difficult to
give ranks to them.

Slide 99
 Rank Correlation

Critical values:
If n  30, critical values are found in Table

If n > 30, use Formula.


Formula rs 
nz
1
where the value of z corresponds to the significance
level. (For example, if  = 0.05, z –
1.96.)
Example: Rankings of Colleges
Use the data in Table to determine if there is a
correlation between the student rankings and the
rankings of the magazine.
Example: Rankings of Colleges
Use the data in Table to determine if there is a
correlation between the student rankings and the
rankings of the magazine.

H 0 : s = 0 H 1 : s  0

Since neither variable has ties in the ranks:

6d 2 6(24)
rs  1   1
n(n 1)
2
8(82 1)
144
 1 504  0.714
 Example: Rankings of Colleges
Use the data in Table to determine if there is a
correlation between the student rankings and
the rankings of the magazine.

H 0 : s = 0 H 1 : s  0

From Table the critical values are 0.738.

Because the test statistic of rs = 0.714 does not
exceed the critical value, we fail to reject the
null hypothesis.
There is not sufficient evidence to support a
claim of a correlation between the rankings of
the students and the magazine.
 Example: Rankings of Colleges
Large Sample Case
Assume that the preceding example is expanded by
including a total of 40 colleges and that the test statistic
rs is found to be 0.300. If the significance level of  =
0.05, what do you conclude about the correlation?

Since n = 40 exceeds 30, we find the critical value

from Formula 13-1

z 1.96
rs    
n 1 0.31440
1
 Example: Rankings of Colleges
Large Sample Case
Assume that the preceding example is expanded by
including a total of 40 colleges and that the test statistic
rs is found to be 0.300. If the significance level of  =
0.05, what do you conclude about the correlation?

The test statistic of rs = 0.300 does not exceed the

critical value of 0.314, so we fail to reject the null
hypothesis.
There is not sufficient evidence to support the claim
of a correlation between students and the
magazine.
 Example: Detecting
a Nonlinear
Pattern
The data in Table are the numbers of games played
and the last scores (in millions) of a Raiders of the
Lost Ark pinball game.
We expect that there should be an association
between the number of games played and the pinball
score.
H 0 : s = 0 H 1 : s  0
 Example: Detecting
a Nonlinear
Pattern
There are no ties among ranks of either list.

6d 2 6(6)
rs  1   1
n(n 1)
2
9(92 1)
36
 1 720 
0.950
 Example: Detecting
a Nonlinear
Pattern
Since n = 9 is less than 30, use Table Critical
values are ± 0.700

The sample statistic 0.950 exceeds 0.700, so

we conclude that there is significant evidence
to reject the null hypothesis of no
correlation.

There appears to be correlation between the

number of games played and the score.
 Example: Detecting
a Nonlinear
Pattern
If the preceding example is done using the methods of
the linear correlation coefficient is r = 0.586.

This leads to the conclusion that there is not enough

evidence to support the claim of a significant linear
correlation, whereas the nonlinear test found that
there was enough evidence. Excel

The Excel scatter diagram

shows that there is a
non-linear relationship
that the parametric method
would not have detected.
 Recap

In this section we have discussed:

Rank correlation which is the non-parametric

equivalent of testing for correlation described.

It uses ranks of matched pairs to test for

association.

Sometimes rank correlation can detect non- linear

correlation that the parametric test will not recognize.
 CHI-SQUARE TEST

 The chi-square distributionis the most frequently employed statistical technique for
the analysis of count (or) frequency data.

 The chi-square statistic is most appropriate for use with categorical variables. i.e.,

Qualitative data, such as marital status, whose values are the categories married,

single, widowed, and divorced.

 The observed frequencies are the number of subjects or objects in our sample that
fall into

the various categories of the variable of interest.

 Expected frequencies are the number of subjects or objects in our sample that we would

expect to observe if some null hypothesis about the variable is true.

 CHI-SQUARE TEST

Applications of Chi-Square test:-

 Hypothesis testing procedures of chi-square test are:
 Tests for proportions,
 Tests of Association, and
 Tests of Goodness-of-fit.

 It can also be used when more than two groups are to be compared.

 h x k contingency table. (h = No. of Rows, k = No.of Columns)

STEPS FOR CALCULATION OF CHI-SQUARE TEST PROCEDURE

(i) State the Null hypothesis:

H0: Two drugs are Same, H1: Two drugs are different
(ii) Calculate the expected frequencies and apply the chi-square test:
Expected Frequency = Row total x Column
total / N
The test statistic for the chi-square test is

Where, O i = Observed value, E i = Expected value

(iii) Find the degree of freedom (d.f.).

d.f. = (c-1)(r-1)
Where c= No. of columns & r = No. of rows.
STEPS FOR CALCULATION OF CHI-SQUARE TEST PROCEDURE

(iv) Probability tables of chi-square test and draw the inferences accordingly.
(v) Draw the conclusions accordingly.

If
(i) 2 < 2 Accept the H and Reject the H (i.e., P >
0.05).
cal. value tab. value => 0 1

(ii) 2 > 2 Reject the H and Accept the H (i.e., P <

0.05).
cal. value tab. value => 0 1
 CHI-SQUARE TEST (PROBLEM): -
1) In an experiment on the immunization of goats from anthrax the following results were obtained.
Derive your inference on the efficacy of the vaccine.

Died Survived Total Oi Ei (O i -E i ) (O i -E i ) 2

Inoculated with vaccine 2 10 12 2 4 -2 4

Not Inoculated 6 6 12 10 8 2 4

Total 8 16 24 6 4 2 4

6 8 2 4
Answer:-
H0: Survival is associated with inoculation
E x pected Frequency (E i )= (Row total x Column total) / N

2 = 4/4 + 4/8 + 4/4 + 4/8 = 1 + 0.5 + 1 + 0.5 = 3

The number of degrees of freedom: (r-1) (c-1) = (2-1) (2-1) = 1.
 The value of 2 at 5% level of significance for one (1) degree of freedom is 3.841.
Interpretation:-
 Hence there is no cause to suspect the hypothesis and the data do not suggest that
the survival is associated with inoculation.
Runs Test for Randomness
 Key Concept
This section introduces the runs test for
randomness, which can be used to determine
whether the sample data in a sequence are in a
random order.
This test is based on sample data that have two
characteristics, and it analyzes runs of those
characteristics to determine whether the runs
appear to result from some random process, or
whether the runs suggest that the order of the
data is not random.
 Runs Test for Randomness
Definitions

A run is a sequence of data having the same

characteristic; the sequence is preceded
and followed by data with a different
characteristic or by no data at all.

The runs test uses the number of runs in a

sequence of sample data to test for
randomness in the order of the data.
 Fundamental Principles
of the Run Test
Reject randomness if the number of runs is very
low or very high.
Example: The sequence of genders FFFFFMMMMM is
not random because it has only 2 runs, so the number
of runs is very low.
Example: The sequence of genders FMFMFMFMFM is
not random because there are 10 runs, which is very
high.
It is important to note that the runs test for
randomness is based on the order in which the
data occur; it is not based on the frequency of
the data.
 Requirements

1. The sample data are arranged according to

some ordering scheme, such as the order
in which the sample values were obtained.

2. Each data value can be categorized into

one of two separate categories (such as
male/female).
 Notation

n1 = number of elements in the

sequence that have one particular
characteristic (The characteristic
chosen for n1 is arbitrary.)

n2 = number of elements in the sequence that

have the other characteristic

G = number of runs
 Runs Test for Randomness
For Small Samples (n1 ≤ 20 and n2 ≤ 20)
and  = 0.05:

Test Statistic
Test statistic is the number of runs G

Critical Values
Critical values are found in Table
 Runs Test for Randomness
For Small Samples (n1 ≤ 20 and n2 ≤ 20)
and  = 0.05:

Decision criteria
Reject randomness if the number of runs G is:
• less than or equal to the smaller critical
value found in Table.
• or greater than or equal to the larger
critical value found in Table.
 Runs Test for Randomness

For Small Samples (n1 ≤ 20 and n2 ≤ 20)

and  = 0.05:
Test Statistic
G  G
z
G
where G  1
n1 
2n1n2
n2
(2n1n2 )(2n1n2  n1 
and G 
(n
n2 )  n ) 2
(n  n
1)
1 2 1 2
 Runs Test for Randomness
For Large Samples (n1 > 20 or n2 > 20) or
 ≠ 0.05:

Critical Values

Critical values of z: Use Z table

 Example: Small Sample
Genders of Bears
Listed below are the genders of the first 10 bears from
Data Set 6 in Appendix B. Use a 0.05 significance level
to test for randomness in the sequence of genders.

MMMMFFMMFF

Separate the runs as shown below.

MMMM FF MM FF

1st run 2nd run 3rd run 4th run

 Example: Small Sample
Genders of Bears
MMMM FF MM FF

1st run 2nd run 3rd run 4th run

n1 = total number of males = 6

n2 = total number of females = 4

G = number of runs = 4
Because n1 ≤ 20 and n2 ≤ 20 and  = 0.05,
the test statistic is G = 4
 Example: Small Sample
Genders of Bears
MMMM FF MM FF

1st run 2nd run 3rd run 4th run

From Table, the critical values are 2 and 9.

Because G = 4 is not less than or equal to 2, nor is
it greater than or equal to 9, we do not reject
randomness.
It appears the sequence of genders is random.
 Example:Large Sample
Boston Rainfall on Mondays
Refer to the rainfall amounts for Boston as listed in Data
Set 10.Is there sufficient evidence to support the claim
that rain on Mondays is not random?

DDDDRDRDDRDDRDDDRDDRRRDDDD
RDRDRRRDRDDDRDDDRDRDDRDDD
R

H0: The sequence is random.

H1: The sequence is not random.

n1 = number of Ds = 33
n2 = number or Rs = 19
G = number of runs = 30
 Example:Large Sample
Boston Rainfall on Mondays
Since n1 > 20, we must calculate z using the formulas:

G  2n1n2 1  2(33)(19) 1  25.115

n1  n2 33
19
(2n1n2 )(2n1n2  n1 
 G  (n  n )2 (n  n 1)
n2 ) 1 2 1 2

 (2)(33)(19)[(2(33)(19)  33 19]
(33 19) 2 (33 19  3.306
1)

G  G 30  25.115
z   1.48
G 3.306
Slide 127
 Example:Large Sample
Boston Rainfall on Mondays

The critical values are z = -1.96 and 1.96.

The test statistic of z = 1.48 does not fall within

the critical region, so we fail to reject the null
hypothesis of randomness.

The given sequence does appear to be

random.

Slide 128
 Recap
In this section we have discussed:
The runs test for randomness
which can be used to determine
whether the sample data in a
sequence are in a random order.
We reject randomness if the
number of runs is very low or very
high.

Slide 129
 You
ha nk
T