MATH 141 Lecture Notes - Lecture 16: Type I And Type Ii Errors, Null Hypothesis, Alternative Hypothesis
7 Dec 2016
School
Department
Course
Professor
Document Summary
Annual profit: a director of ford dealership would like to see if their annual profit is higher than last year. -- we try our best to get correct answer and avoid the risk of wrong one. Hypothesis: hypothesis is a statement we are going to test using your sample data. This statement can be either correct or incorrect. ) and threshold value, connected always using: express alternative: we will use either, >, or < to describe the assumption. Remark: the alternative hypothesis allows non (cid:862)equal(cid:863) (cid:272)ases o(cid:374)ly. You are going to draw a conclusion about unknown things => guessing using some evidence. You may get a correct conclusion; or maybe you are wrong. Thus we may have one of following issues. Two possible errors (risks: type i error( ): the probability of rejecting a true null hypothesis h0. This error is being controlled by significant level: type ii error( ): the probability of accepting a false null hypothesis.
