There isn't enough information here to answer. Non-parametric tests should not be a goal, in and of itself. They are inherently less powerful than parametric tests, but less biased in the event assumptions substantially fail. Your survey should be constructed to test your hypothesis. The subsequent tests should be based on the nature of the data you were able to collect and need to be determined ex ante, not after you have the data in hand.
Your thought process should be:
What is my hypothesis and alternative hypothesis?
What type of data can I reasonably expect to collect?
Can I validate my collection mechanism?
Due to the nature of the question and the collection tools, what types of statistical tools will I need to use?
Subscribe to:
Post Comments (Atom)
No comments:
Post a Comment