ECON 2142 Lecture Notes - Lecture 3: Statistical Hypothesis Testing, Decision Rule, Test Statistic
16 Mar 2017
School
Department
Course
Professor
Document Summary
Hypothesis testing for one mean: using the z-test, using the t-test. Assumptions: the value of the population standard deviation is known, we are sampling from a population which is normally distributed. If the sample is large enough (n>30) then the sample distribution of the mean becomes normal. One-tail versus two-tail testing determined by whether you"re looking if the population is equal (one-tail) or more/less non-directional testing versus directional testing. Critical values: (when using a non-cumulative z-table) 0. 5 - /2 ( =the significance level, and you divide by 2 because it"s a two-tail test, aka there are two rejection regions) Test statistic: x 0 z = / n. 0 = value for the population mean specified in the null hypothesis. = population standard deviation n= sample size. = standard error for sampling distribution of the mean. Decision rule: reject h 0 if value of z > upper critical value or < lower critical value.
