Mann Whitney U test

5,781 views 29 slides Aug 14, 2018
Slide 1
Slide 1 of 29
Slide 1
1
Slide 2
2
Slide 3
3
Slide 4
4
Slide 5
5
Slide 6
6
Slide 7
7
Slide 8
8
Slide 9
9
Slide 10
10
Slide 11
11
Slide 12
12
Slide 13
13
Slide 14
14
Slide 15
15
Slide 16
16
Slide 17
17
Slide 18
18
Slide 19
19
Slide 20
20
Slide 21
21
Slide 22
22
Slide 23
23
Slide 24
24
Slide 25
25
Slide 26
26
Slide 27
27
Slide 28
28
Slide 29
29

About This Presentation

This presentation contains information about Mann Whitney U test, what is it, when to use it and how to use it. I have also put an example so that it may help you to easily understand it.


Slide Content

Mann Whitney U test:
By: Dr. Ankit Gaur (B.Pharm, M.Sc, Pharm.D, RPh)

Use when:
• Data does not support means (ordinal)
• Data is not normally distributed.
Nonparametric tests:
Tests without population parameters
(means and standard deviations)

1) Rank all data.
2) Evaluate if ranks tend to
cluster within a group.

Mann Whitney U test:
nonparametric equivalent of a t test
for two independent samples

Mann Whitney U test:
Where:n
1
n
2
()()
( )
()()
( )
Unn
nn
R
U nn
nn
R
1 1 2
11
1
2 1 2
22
2
1
2
1
2
= +
+
-
= +
+
-
å
å
Size of sample one
Size of sample two

Mann Whitney U test:
Where:
()()
( )
()()
( )
Unn
nn
R
U nn
nn
R
1 1 2
11
1
2 1 2
22
2
1
2
1
2
= +
+
-
= +
+
-
å
å
R

Sum of sample one ranks
R

Sum of sample two ranks

Evaluation of Mann Whitney U
1) Choose the smaller of the two U values.
2) Find the critical value (Mann Whitney table)
3) When computed value is smaller than the
critical value the outcome is significant!

group 1 group 2
24 28
18 42
45 63
57 57
12 90
30 68

group 1 group 2
24 28
18 2 42
45 63
57 57
12 1 90
30 68
Step One: Rank all data across groups

group 1 group 2
24 3 28 4
18 2 42
45 63
57 57
12 1 90
30 68

group 1 group 2
24 3 28 4
18 2 42 6
45 7 63
57 57
12 1 90
30 5 68

Tied ranks:
• Find all values that are tied.
• Identify all ranks that would be
assigned to those values.
• Average those ranks.
• Assign that average to all tied values.

group 1 group 2
24 3 28 4
18 2 42 6
45 7 63
57 57
12 1 90
30 5 68

8th and 9th ranks would be used.
8+9 = 17 Averaging
17/ 2 = 8.5 ranks

group 1 group 2
24 3 28 4
18 2 42 6
45 7 63
57 8.5 57 8.5
12 1 90
30 5 68

group 1 group 2
24 3 28 4
18 2 42 6
45 7 63 10
57 8.5 57 8.5
12 1 90 12
30 5 68 11

group 1 group 2
24 3 28 4
18 2 42 6
45 7 63 10
57 8.5 57 8.5
12 1 90 12
30 5 68 11
26.5 51.5
Step Two: Sum the ranks for each group

( )
R
nn
=
+
å
1
2
Check the rankings:

( )()
R
R
R
=
=
=
å
å
å
1213
2
156
2
78

group 1 group 2
24 3 28 4
18 2 42 6
45 7 63 10
57 8.5 57 8.5
12 1 90 12
30 5 68 11
26.5 51.5

26.5 + 51.5 = 78

()()
( )
Unn
nn
R
1 1 2
11
1
1
2
= +
+

Step Three: Compute U
1

()()
( )
()()
()
Unn
nn
R
U
U
U
1 1 2
11
1
1
1
1
1
2
66
67
2
265
3621265
305
= +
+
-
= + -
=+-
=
å
.
.
.

()()
( )
U nn
nn
R
2 1 2
22
2
1
2
= +
+

Step Four: Compute U
2

()()
( )
()()
()
U nn
nn
R
U
U
U
2 1 2
22
2
2
2
2
1
2
66
67
2
515
3621515
55
= +
+
-
= + -
=+-
=
å
.
.
.

U
U
U
1
2
305
55
55305
55
=
=
<
=
.
.
. .
.
Step Five: Compare U
1
to U
2

Critical Value = 5
This is a nonsignificant outcome

group 1 group 2
24 3 28 4
18 2 42 6
45 7 63 10
57 8.5 57 8.5
12 1 90 12
30 5 68 11

Thank you… “Believe in yourself
those who do not believe in
themselves cannot achieve
anything in their lives.