Biology 2244A/B Lecture Notes - Lecture 9: Qualitative Property, Null Hypothesis, Statistical Hypothesis Testing

• School: Western University
• Department: Biology
• Course: Biology 2244A/B
• Professor: Vicki Olds

Document Summary

The rare event rule: if the probability under a given assumption of a particular observed result is small, then the assumption is probably not correct. In this question, our first step is to figure out what our claim is: formalize the claim, null hypothesis (h0) = Claims are always written in the context of the parameter that (cid:449)e"(cid:396)e e(cid:448)aluati(cid:374)g: we never make claims based on samples, that is why we make hypotheses based on p and not ^p. Two-tailed/two-sided tests evaluate whether a parameter differs from some value. One-tailed/one-sided tests have directionality; evaluates whether a parameter is greater than/less than some value. The (cid:374)ull h(cid:455)pothesis is al(cid:449)a(cid:455)s e(cid:454)p(cid:396)essed as (cid:862)e(cid:395)uals . (cid:863: alte(cid:396)(cid:374)ati(cid:448)e h(cid:455)pothesis is (cid:449)he(cid:396)e (cid:449)e put i(cid:374) the (cid:862)g(cid:396)eate(cid:396) tha(cid:374)/less tha(cid:374)/diffe(cid:396)e(cid:374)t tha(cid:374) (cid:863) The direction of the greater than/less than value dictates which tail we are evaluating: so when we say one-sided test, we must clarify the direction of the tail.