This preview shows pages 1–4. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: Module 12 Errors, Power and Sample Size Power of Hypothesis Tests and Sample Size Objectives: One should be able to • define the types of errors associated with hypothesis tests • determine the power associated with a ztest • choose appropriate sample sizes based on power calculations Key ideas: Logic of Hypothesis Testing • We are using sample data to infer about a larger population. • Two mutually exclusive and exhaustive statements will be constructed. • One statement will be considered true unless sufficient evidence suggests it should be rejected as false. What does it mean? We have devised a procedure that controls the probability of incorrectly rejecting H o . Suppose we do not reject H o . Is the null hypothesis true or do we simply have too little evidence to reject H o ? Possible Decisions: A Court of Law Correct Decision Innocent person goes to jail Convict Guilty person is free Correct Decision Acquit Guilty Innocent Reality: Decision H o : Innocent Assume true until inconsistent with evidence Possible Decisions: Correct Decision Type I error Reject H o Type II error Correct Decision Do Not Reject H o False True Reality: H o is Decision Vocabulary: • Type I Error: rejecting H o when it is in fact true. • Type II Error: not rejecting H o when it is false....
View Full
Document
 Spring '09
 KIN

Click to edit the document details