What do I do when my Welch test and Mann-Whitney tests have conflicting p-values/ interpretations?
Independent Samples T-Test |
|||||||||
Test |
Statistic |
df |
p |
||||||
Lead_Measured_(mg/kg) |
Student |
-2.048 |
90.000 |
0.044 |
|||||
Welch |
-2.048 |
64.477 |
0.045 |
||||||
Mann-Whitney |
920.500 |
0.285 |
|||||||
Table 3. A Student, Welch, and Mann-Whitney t-test.
This is what I have collected from my data, and I do not know how to properly interpret it.
My confidence level is 95% with and alpha value of 5%.
The p-values are conflicting because the Welch test is a parametric test and Mann-Whitney is a non-parametric test.
If the Lead_Measured variable is normally distributed then make the interpretation based on the Welch test, otherwise use the p-value of the Mann-Whitney test because the Welch test requires the assumption that the variable is normally distributed.
If the p-value is greater than 0.05 that means there is not a significant difference and when it is less than 0.05 that means there is a significant difference in the given problem.
If you have more questions you can send them to us and we will try our best to help you out.
Good luck with your studies!!!
Get Answers For Free
Most questions answered within 1 hours.