I have a psyche project due and I am kicking myself in the face for forgetting all my stats lessons. I have two sets of data and I want to show that they are significantly different. What tests do I use for this? The distributions are not normal.
Statistics: How to test if two datasets are different?
Here is a reference for a non-parametric test (Mann-Whitney test) that does not require the normality assumption. You could give it a shot.
By using a t-test when the normality assumption is violated, it has been proven that the bias or error is not that significant. Should you wish, you can also do the t-test and compare the results.
No comments:
Post a Comment