Statistical Sciences 2244A/B Lecture 13: 2244-Lec 13 Hypothesis testing III
Document Summary
Question: suppose we set a signi cance level of alpha = 0. 05 to use as our criterion of what"s too small to happen due to chance alone". We are assuming p is equal to p(not) If p is less than or equal to our signi cant value we reject our null ho. If our sample is anything other than zero its possible to get the sample proportions that are unlikely. This is the only form of error that actually means mistake unlike sampling error which is expected and can be predicted. When p is less than or equal to our signi cance value we reject ho. When p is greater than our signi cance value we accept ho. The only thing we know is ho will be accepted or rejected. Type 1 error is rejecting the ho when it was actually true so we should not have rejected.