Scribd
Upload
52 views3 pages

Non-Parametric Methods - 1 PDF

The document defines several nonparametric statistical tests: 1) The Wilcoxon Signed Rank Test compares the median of a population to a specified value by ranking differences and summing positive ranks. 2) The Mann-Whitney U Test compares two independent populations by combining and ranking samples and calculating the sums of ranks for each sample. 3) The Kolmogorov-Smirnov Two-Sample Test compares the cumulative distribution functions of two samples by calculating the maximum vertical difference between the empirical distribution functions. 4) A permutation is defined as a rearrangement of objects into distinguishable sequences, with the number of permutations calculated as nPr.

Uploaded by

Rajkamal79
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
52 views3 pages

Non-Parametric Methods - 1 PDF

The document defines several nonparametric statistical tests: 1) The Wilcoxon Signed Rank Test compares the median of a population to a specified value by ranking differences and summing positive ranks. 2) The Mann-Whitney U Test compares two independent populations by combining and ranking samples and calculating the sums of ranks for each sample. 3) The Kolmogorov-Smirnov Two-Sample Test compares the cumulative distribution functions of two samples by calculating the maximum vertical difference between the empirical distribution functions. 4) A permutation is defined as a rearrangement of objects into distinguishable sequences, with the number of permutations calculated as nPr.

Uploaded by

Rajkamal79
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

1. How would you define the Wilcoxon Signed Rank Test?

Wilcoxon Signed Rank Test:


Let be the median of the population under study with density f x .
The null and alternative hypotheses for the Wilcoxon Signed Rank Test are,
H 0 : 0
H a : 0
Level of significance, Choose 1% or 5% or 10%.
Procedure to calculate the test statistic:
Let X 1 , X 2 ,

, X n is a random sample drawn to perform this test.

Step 1: Subtract 0 from each X i , i.e. di X i 0 , i 1, 2, 3,

, n.

Step 2: Make the differences as positive by taking absolute values,


i.e. X i 0 , i 1, 2,3,

, n. Ignore '0' deviations while ranking.

Step 3: Rank the absolute differences in order from smallest 1 to largest n .


In the case of ties use average of the ranks as the common rank.
Step 4: Give each rank the same sign as the sign that is possessed by the actual
difference, i.e. X i 0 .
Step 5: Test Statistic, W Sum of positive ranks.
Conclusion: If the calculated test statistic, W is less than or equal to the critical value given in
the table corresponding to the value n* , the size of the sample after removing '0' deviations,
reject the null hypothesis, otherwise fail to reject it.
If n* 25, use the normal approximation to test the above null hypothesis with the following
Z -statistic.
Z

W n n 1 4
n n 1 2n 1 24

___________________________________________________________________________
For two-sample case we can use the above test procedure with the following modifications.
Let f x & f y are the densities of the two populations under comparison.
Let be the population median of the differences of the two populations under comparison.
H 0 : f x f y , i.e. 0
H a : f x f y , i.e. 0
Let X 1 , X 2 ,

, X n and Y1 , Y2 ,

, Yn are the random samples drawn from the two populations

to perform this test.


Obtain the differences, di X i Y1 , i 1, 2,3,

, n.

Rest of the steps are same to perform Wilcoxon-test for the difference of two populations.

2. How would you define the Mann-Whitney Statistic?


Mann-Whitney Statistic:
Let X 1 , X 2 ,

, X n and Y1 , Y2 ,

, Ym are the random samples drawn from the two populations

to perform this test.


Then combine both the samples and rank those n m values from smallest 1 to largest

n m . In the case of ties use average of the ranks as the common rank.
Let W be the sum of ranks of sample 1 and V be the sum of ranks of sample 2. Then calculate,
U1 nm

n n 1

W
2
m m 1
U 2 nm
V U 2 nm U1
2
Then the Mann-Whitney Statistic, U is defined as,
U min U1 , U 2

3. Calculate at 5% significance level, Mann-Whitney Statistic U of a disease study, when the


sum of the ranks W is 100; normal set m is 3 and the disease set n is 10.
For W = 100, m = 3, and n = 10, the p-value of the test, P W 100 | m 3, n 10 0.5315.
For p-value the following table was used.
Since p-value > 0.05 = , data provides no sufficient evidence to reject the null hypothesis that
both normal and disease distributions are identical.

4. Define Kolmogorov-Smirnov Two- Sample test.


Let FX x & FY y are the cdf's of the two populations under comparison.
Let X 1 , X 2 ,

, X n and Y1 , Y2 ,

, Yn are the random samples drawn from the two populations

to perform this test.


The null and alternative hypotheses for the Kolmogrov-Smirnov's Test are,
H 0 : FX x FY y
H a : FX x FY y
Level of significance, Choose 1% or 5% or 10%.
Test statistic, Dn ,m sup FX t FY t
t

The above test statistic has asymptotic Kolmogorov-Smirnov's distribution.


Using technology obtain the p-value and if the obtained p-value , reject the null hypothesis,
otherwise fail to reject the null hypothesis.

5. Define Permutation.

Permutation is the rearrangement of objects or symbols into distinguishable sequences. Each


unique ordering is called a permutation.
The number of permutations with r elements from n objects is, n Pr or P n, r

n!
n r !

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy