Chapter 9 10 11 综合.pptVIP

* STAT Chapter 9 　Hypothesis testing Hypothesis testing exits anywhere anytime in life. We need to measure the length and weight of basic commodities. We need to examine the quality of production. We need to check the students’ score and foundation when enrolling. Compared with parameter testing, hypothesis testing is given a claim. What we should do is testing the validity of a claim. When testing, we first choose a proper sample, then calculate the statistic inference to make judgment. But as we know, sample is not exactly the population, which may causes a validity of population but a invalidity of sample or a validity of sample but a invalidity of population. What hypothesis should do is make judgment only in one test. Keystone: the fundamental thinking, working principle, method of hypothesis testing Difficulty: multifarious formula and differences between them 9.1 Null and alternative hypotheses Testing research hypothesis Testing the Validity of a claim Testing in Decision-Making Situation summary of Form for null and alternative hypotheses let denote the specific numerical value being considered in the null and alternative hypotheses. In general, a hypothesis test about the value of a population mean must take one of the following three forms 9.2 Type 1 and type 2 errors Reject the true null hypothesis --------reject truth Accept the false null hypothesis-------accept false Population Condition H0 True Ha True Accept H0 correct conclusion Type 2 Error conclusion Reject H0 Type 1 Error correct conclusion We denote the probabilities of making the two errors as follows α=the probability of making Type 1 error β=the probability of making Type 2 error 9.3 One-ta