In: Statistics and Probability
Most people believe you shouldn’t use a Mann-Whitney test if the data is interval/ratio, symmetric, and normal. They think a t-test is better. Why might this be?
When can a z-test successfully be used instead of a chi-square test (for the same data)?
Mann-Whitney test is a non parametric test and the most widely used test as an alternative to the t-test when we do not make the t-test assumptions about the parent population. When the data is interval/ratio, symmetric and normal which is considered as an assumption of the parent population for t-test, then t-test is better.
Chi square test is a general test. It is a non parametric test. That is, it is not based on any parametric assumption on the parent population. It is also used as a parametric test, because it is the test of the significance difference between the true value and the hypothetical value of the population variance i.e. it is also used to test H0 : . On the other hand Z test is a parametric test. In other words, Z test can successfully used when the parent population is assumed to be normal and the population standard deviation is given or known.