Lecture18standard

# Lecture18standard - Statistics 511 Statistical Methods Dr Levine Purdue University Spring 2011 Lecture 17 P-values and some Additional Issues

This preview shows pages 1–8. Sign up to view the full content.

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Statistics 511: Statistical Methods Dr. Levine Purdue University Spring 2011 Lecture 17: P-values and some Additional Issues concerning Testing Devore: Section 8.4-8.5 April, 2011 Page 1 Statistics 511: Statistical Methods Dr. Levine Purdue University Spring 2011 The Need for P-values • There are two main problems with the rejection region based approach to testing: 1. It says nothing about where exactly the value of test statistic fell in the rejection region. 2. It imposes the specified significance level on other decision makers April, 2011 Page 2 Statistics 511: Statistical Methods Dr. Levine Purdue University Spring 2011 Example I • Discarded batteries are a significant source of urban storm water contamination (especially in terms of zinc). A sample of 51 Panasonic AAA batteries gave a sample mean zinc mass of 2 . 06 g and a sample standard deviation of . 141 g. Does this data provide compelling evidence for concluding that the population mean zinc mass exceeds 2 . g? • The hypotheses involved are H : μ = 2 . vs. H a : μ > 2 . • The test statistic is z = ¯ x- 2 . s √ n = 3 . 04 April, 2011 Page 3 Statistics 511: Statistical Methods Dr. Levine Purdue University Spring 2011 Example II • The values of ¯ x that are at least as contradictory to the null hypothesis as 2 . 06 are all those that exceed 2 . 06 . They correspond to the values of z that exceed 3 . 04 • The probability that the sample-based statistic z exceeds the current value under the null hypothesis is P ( Z > 3 . 04 when μ = 2 . 0) = 1- Φ(3 . 04) = 0 . 012 April, 2011 Page 4 Statistics 511: Statistical Methods Dr. Levine Purdue University Spring 2011 P-value definition • The P-value is the probability, calculated assuming that the null hypothesis is true, of obtaining a value of the test statistic at least as contradictory to H as the value calculated from the available sample. • Important points: 1. The P-value is a probability 2. This probability is calculated assuming that the null hypothesis is true 3. The P-value is NOT the probability that H is true, nor is it an error probability April, 2011 Page 5 Statistics 511: Statistical Methods Dr. Levine Purdue University Spring 2011 Decision rule based on the P-value • Clearly, if the significance level chosen is α , then 1. Reject H if P-value ≤ α 2. Do not reject H if P-value > α April, 2011 Page 6 Statistics 511: Statistical Methods Dr. Levine Purdue University Spring 2011 Example • The nicotine content problem involves testing...
View Full Document

## This note was uploaded on 02/20/2012 for the course STAT 511 taught by Professor Bud during the Fall '08 term at Purdue University-West Lafayette.

### Page1 / 22

Lecture18standard - Statistics 511 Statistical Methods Dr Levine Purdue University Spring 2011 Lecture 17 P-values and some Additional Issues

This preview shows document pages 1 - 8. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online