This preview has intentionally blurred sections. Sign up to view the full version.View Full Document
Unformatted text preview: March 15th Chapter 6 (continued) Hypothesis Testing Example. H ( null hypothesis ) : the average height is 5’8” or more. ( : 5'8") H μ ≥ a H ( alternative hypothesis ) : the average height is less than 5’8” ( : 5'8") a H μ p Example . (law suit) O.J. Simpson case H : O.J. is innocent. ( original belief ) a H : O.J. is guilty. Truth H a H Decision H Correct Decision Type II error a H Type I error Correct Decision ( T y p e I e r r o r ) ( R e j e c t | ) P P H H α = = This probability is called the significance level of the test . Scenario 1 : Inference on one population mean μ (normal population, 2 σ is known) There are two methods. 1. Pivotal Quantity Method (We will learn this method first.) 2. Likelihood Ratio Test (We will learn this method later.) 1 Now we introduce the general procedures in the Pivotal Quantity method. 1. Before deriving the test, you must know your Pivotal Quantity for the given problem: ~ (0,1) X Z N n μ σ- = 2. Now you can start your hypothesis test. First write down your hypotheses. There are 3 cases (or choices). You need to choose the one that is most suitable for your given problem. a. (one-sided test) : or equivalently, : : : a a H H H H μ μ μ μ μ μ μ μ ≤ = f f b. (one-sided test) : or equivalently, : : : a a H H H H μ μ μ μ μ μ μ μ ≥ = p p c. (two-sided test) : : a H H μ μ μ μ =...
View Full Document
This note was uploaded on 11/14/2010 for the course AMS 312 taught by Professor Zhu,w during the Spring '08 term at SUNY Stony Brook.
- Spring '08