Q 589. Mann Whitney Test is considered as an alternative to a T-test. What are the differences in the assumptions of the two tests? Provided examples where Mann Whitney test is better suited than a T-test.

 

Note for website visitors -

• This platform hosts two weekly questions, one on Tuesday and the other on Friday. 
• All previous questions can be found here: https://www.benchmarksixsigma.com/forum/lean-six-sigma-business-excellence-questions/. 
• To participate in the current question, please visit the forum homepage at https://www.benchmarksixsigma.com/forum/.
• The question will be open until Tuesday or Friday at 5 PM Indian Standard Time, depending on the launch day. 
• Responses will not be visible until they are reviewed, and only non-plagiarised answers with less than 5-10% plagiarism will be approved. 
• If you are unsure about plagiarism, please check your answer using a plagiarism checker tool such as https://smallseotools.com/plagiarism-checker/ before submitting. 
• All correct answers shall be published, and the top-rated answer will be displayed first. The author will receive an honorable mention in our Business Excellence dictionary at https://www.benchmarksixsigma.com/forum/business-excellence-dictionary-glossary/ along with the related term.

• Some people seem to be using AI platforms to find forum answers. This is a risky approach as AI responses are error prone as our questions are application-oriented (they are never straightforward). Have a look at this funny example - https://www.benchmarksixsigma.com/forum/topic/39458-using-ai-to-respond-to-forum-questions/

• We also use an AI content detector at https://crossplag.com/ai-content-detector/. Only answers with less than 15-20% AI-generated content will be approved.

Mann Whitney test

 

This test is known as Wilcoxon rank-sum test.

It is a non-parametric statistical test which is generally used to review the distributions between two independent groups.

This is also an alternative to T-test, but we should use this test when our assumptions of normality and equal variances generally not met. This test is also applied to check that medians of two groups are statistically different from each other or not?

 

This test works on below parameters:

·       Ranking

·       Calculating U

·       Comparison      

·       Hypothesis testing

·       Interpretations

 

	Mann Whitney	T test
Assumptions	No specific distribution assumptions Applied when data is non-normal and skewed. Comparing Rank between 2 groups	Assumes data follows a normal distribution. Comparing with 2 groups with equal variances

 

Real scenario where Mann-Whitney U test accepts more than T-test.

ü  When data is ordinal

ü  When we have small samples

ü  When we have outliers

ü  When our data is skewed

ü  When variances are not equal

ü  When we have categorical data to compare

 

 

 

	Mann Whitney Test		T- test
Assumptions	There is no requirement of 1. Random data 2.Depend data need not to be normal 3. Variance need not to be equal as prerequisite		1. Data needs to be continuous 2.Data variance in each group should be similar 3.Dependent data should be normally distributed

an whitney test is most suitable in the case when Our dependent data i.e  (Y) is continuous but non normally distributed and we have two groups  of X factors and we want to test the significance level of X / find that wether X is having impact on Y or not i.e the medians of X are similar of different.

Pradeep Shukla has provided the best answer from the ones published.

 

Note: Many answers are not getting published. Top reasons

1. High AI-generated content

2. High plagiarism

Request all respondents to ensure adherence to the guidelines for your answer to get published.

- Responses will not be visible until they are reviewed, and only non-plagiarised answers with less than 5-10% plagiarism will be approved (use https://smallseotools.com/plagiarism-checker/ to check for plagiarism)

- We also use an AI content detector at https://crossplag.com/ai-content-detector/. Only answers with less than 15-20% AI-generated content will be approved.