Statistical Perspectives Different tests for a difference: how do we do research?

• Frequentist probability concerns the possibility of NO difference • The starting premise is a population with known features • Bayes’ theories concern modifying a pre-existing possibility • Experiments revise the previous estimate • Lab experiments do not often use random samples • Small numbers, random allocation to treatment • Well suited to permutation tests • Choose the test when you devise the experiment • Make sure that the equipment (and the test) are appropriate