Download presentation
Presentation is loading. Please wait.
1
Rank Order Correlation
Dr. Anshul Singh Thapa
2
Introduction Spearman’s rank correlation was developed by the British psychologist C.E. Spearman. It is used when the variables cannot be measured meaningfully. Ranking may be more meaningful when the measurements of variables are suspect. Consider the situation where we are required to calculate the correlation between height and weight of students in a remote village. Neither measuring rods nor weighing scales are available. The students can be easily ranked in terms of height and weight without using measuring rods and weighing scales.
3
There are also situations when you are required to quantify qualities such as fairness, honesty etc. Ranking may be a better alternative to quantification of qualities. Moreover, sometimes the correlation coefficient between two variables with extreme values may be quite different from the coefficient without the extreme values. Under these circumstances rank correlation provides a better alternative to simple correlation. Rank correlation coefficient and simple correlation coefficient have the same interpretation. Its formula has been derived from simple correlation coefficient where individual values have been replaced by ranks. These ranks are used for the calculation of correlation. This coefficient provides a measure of linear association between ranks assigned to these units, not their values.
4
The calculation of rank correlation will be illustrated under three situations.
The ranks are given. The ranks are not given. They have to be worked out from the data. Ranks are repeated.
5
The ranks are given A B 6 3 5 8 4 10 9 2 1 7
6
Solution: R1 R2 (R1 – R2) D 6 3 5 8 4 -1 10 9 1 2 -2 7
7
Solution: R1 R2 (R1 – R2) D (R1 – R2)2 D2 6 3 9 5 8 4 -1 1 10 2 -2 7
8
Solution: rs = 0.782 R1 R2 (R1 – R2) D (R1 – R2)2 D2 6 3 9 5 8 4 -1 1
10 2 -2 7 ΣD2 = 36 rs = 0.782
9
The ranks are not given. They have to be worked out from the data
Year A B 1 97.8 73.2 2 99.2 85.8 3 98.8 78.9 4 98.3 75.8 5 98.4 77.2 6 96.7 87.2 7 97.1 83.8
10
Solution Year A R1 1 97.8 3 2 99.2 7 98.8 6 4 98.3 5 98.4 96.7 97.1
11
Solution Year A R1 B R2 1 97.8 3 73.2 2 99.2 7 85.8 6 98.8 78.9 4 98.3 75.8 5 98.4 77.2 96.7 87.2 97.1 83.8
12
Solution Year A R1 B R2 (R1 – R2) D 1 97.8 3 73.2 2 99.2 7 85.8 6 98.8
78.9 4 98.3 75.8 5 98.4 77.2 96.7 87.2 -6 97.1 83.8 -3
13
Solution Year A R1 B R2 (R1 – R2) D (R1 – R2)2 D2 1 97.8 3 73.2 2 4
99.2 7 85.8 6 98.8 78.9 98.3 75.8 5 98.4 77.2 96.7 87.2 -6 36 97.1 83.8 -3 9
14
Solution rs = -0.107 Year A R1 B R2 (R1 – R2) D (R1 – R2)2 D2 1 97.8 3
73.2 2 4 99.2 7 85.8 6 98.8 78.9 98.3 75.8 5 98.4 77.2 96.7 87.2 -6 36 97.1 83.8 -3 9 ΣD2 = 62 rs =
15
Ranks are repeated A B 50 110 55 65 115 125 140 60 130 120 70 75 160
16
It may be noted that in series X, 50 has repeated thrice (m = 3), 55 has been repeated twice (m = 2), 65 has been repeated twice (m = 2). In series Y, 110 has been repeated twice (m = 2), and 115 has been repeated thrice (m = 3) A B 50 110 55 65 115 125 140 60 130 120 70 75 160
17
Solution A R1 50 2 55 4.5 65 7.5 60 6 70 9 75 10
18
Solution A R1 B R2 50 2 110 1.5 55 4.5 65 7.5 115 4 125 7 140 9 60 6 130 8 120 70 75 10 160
19
Solution A R1 B R2 (R1 – R2) D 50 2 110 1.5 0.5 55 4.5 3 65 7.5 115 4 3.5 125 7 -5 140 9 -4.5 60 6 130 8 -6 120 70 5 75 10 160
20
Solution A R1 B R2 (R1 – R2) D (R1 – R2)2 D2 50 2 110 1.5 0.5 0.25 55
4.5 3 9.00 65 7.5 115 4 3.5 12.25 125 7 -5 25.00 140 9 -4.5 20.25 60 6 4.00 130 8 -6 36.00 120 2.25 70 5 75 10 160 00.00
21
Solution rs = 0.155 A R1 B R2 (R1 – R2) D (R1 – R2)2 D2 50 2 110 1.5
0.5 0.25 55 4.5 3 9.00 65 7.5 115 4 3.5 12.25 125 7 -5 25.00 140 9 -4.5 20.25 60 6 4.00 130 8 -6 36.00 120 2.25 70 5 75 10 160 00.00 ΣD2 = 134 rs = 0.155
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.