Scribd
Upload
26 views

Module 14 Non Parametric Statistics Spearman Rank Order Correlation1 2

1. Non-parametric statistics do not assume a normal distribution and can be used with ordinal or ranked data. They include tests like the Spearman rank-order correlation, Kendall's tau, and the Mann-Whitney U test. 2. The Spearman rank-order correlation (Spearman's rho) is a non-parametric measure of correlation that assesses how well the relationship between two variables can be described using a monotonic function. 3. It is calculated by ranking all data values from lowest to highest for each variable, calculating the differences between ranks for each observation, summing the squared differences, and using the formula to determine the correlation coefficient. A significant positive correlation indicates a strong relationship

Uploaded by

Joy Ducusin
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
26 views

Module 14 Non Parametric Statistics Spearman Rank Order Correlation1 2

1. Non-parametric statistics do not assume a normal distribution and can be used with ordinal or ranked data. They include tests like the Spearman rank-order correlation, Kendall's tau, and the Mann-Whitney U test. 2. The Spearman rank-order correlation (Spearman's rho) is a non-parametric measure of correlation that assesses how well the relationship between two variables can be described using a monotonic function. 3. It is calculated by ranking all data values from lowest to highest for each variable, calculating the differences between ranks for each observation, summing the squared differences, and using the formula to determine the correlation coefficient. A significant positive correlation indicates a strong relationship

Uploaded by

Joy Ducusin
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 3

MODULE 14

NON-PARAMETRIC STATISTICS: NATURE AND SPEARMAN RANK-ORDER CORRELATION

==================================================================================
OBJECTIVES: At the end of the lesson, the students are expected to:

1. Discuss the nature of non-parametric statistics.

2. Explain when to use Spearman Rank- Order correlation.

3. Solve statistical problems using Spearman Rank- Order correlation.

==================================================================================

Nature of Non-parametric Statistics

 Non-parametric test which is also called distribution-free statistics because it is free from
the assumption of a normal distribution in the population being studied.
 Non-parametric tests are used when dealing with nominal (counting) or ordinal data
(ranking).
 If the independent variables are non-metric, the non-parametric test is usually performed.
 Some non-parametric tests do not require a large sample.
 Some non-parametric tests are the Spearman Rank-Order Correlation, Kendal Tau Coefficient of
Concordance, the Chi-Square Test, the Kruskal Wallis-H Test and Mann Whitney-U test.

SPEARMAN RANK-ORDER CORRELATION ( SPEARMAN’S RHO)

 Non-parametric correlation statistic are used if the data are expressed in rank or data that are
converted into ranks (ordinal data).
 It is an alternative method to the Pearson Product-moment Correlation if the sample size is
small.

Formula : r = 1 – _6 (∑D2)__
N (N2 – 1)
Example:

Let X = GWA in College


Y = Annual Income in Thousand Php.

Respondent X Y Rx Ry D D2
A 86 287 2 1 1 1
B 79 138 7 6.5 .5 .25
C 84 200 4 4 0 0
D 91 245 1 2 1 1
E 82 200 5 4 1 1
F 77 125 8 8 0 0
G 80 138 6 6.5 .5 .25
H 85 200 3 4 1 1
∑= 4.5

Required: Determine if there is a significant correlation between GWA and Annual Income.
Use .01. Interpret result.

Steps:

1. State alternative hypotheses.

Ho: There is no significant correlation between GWA and annual income.


Ha: there is a significant correlation between GWA and annual income.

2. Rank the data. Follow rules in ranking.


3. Solve the correlation coefficient

rs = 1 – _6 (∑D2)__
N (N2 – 1)

rs = 1 – 6(4.5) = 1 – 27/8(63) = 1 – 27/504 = 1 – .054 = .95


8 (82 – 1)

4. Test the significance of the correlation.

n= 12 ; r.01= .678

rs= .95> r.01= .678: The computed correlation coefficient is significant; REJECT Ho.
5. Interpretation/Conclusion

There is a significant correlation between GWA and annual income. A very


high positive correlation is evident indicating a very strong positive relationship
between GWA and annual income.

You might also like