This preview shows pages 1–6. 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 DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: Public Health 6450 Fall 2011 Andrew Mugglin and Lynn Eberly Division of Biostatistics School of Public Health University of Minnesota ph6450@biostat.umn.edu Part 11 Review Revisiting Important Concepts Extending the Ideas Behind Hypothesis Tests for Where are we going? Previously: Tests and CIs for : known (use z and , Chapter 6.16.2) Tests and CIs for : unknown (use t and s , Chapter 7.1) Errors and power in significance testing (Chapter 6.36.4) Current topics: Extending the ideas behind hypothesis tests for Linking tests with CIs (Chapter 6.2) Hypothesis tests for matched pairs (Chapter 7.1) Sample size calculations (not in M,M&C) (Interval estimates and hypothesis testing for the Binomial will be covered in Ch. 8.) Mugglin and Eberly PubH 6450 Fall 2011 Part 11 2 / 21 Review Revisiting Important Concepts Extending the Ideas Behind Hypothesis Tests for Interpretations of a pvalue The pvalue gives the probability of X being far away from . Suppose we got a test statistic of t = 2 . 7 with df = 18 and p = 0 . 01. Incorrect: The probability that the null hypothesis is true is . 01. Incorrect: The probability of observing t = 2 . 7 when H is true is 0 . 01. Incorrect: The probability of observing such a large X due to chance is 0 . 01. Correct: The probability of observing a test statistic with a value as or more extreme than t = 2 . 7 when H is true is 0 . 01. Correct: The smaller the pvalue, the stronger the evidence against H . Mugglin and Eberly PubH 6450 Fall 2011 Part 11 3 / 21 Review Revisiting Important Concepts Extending the Ideas Behind Hypothesis Tests for Significance tests come from rejection rules First, choose and find the z * that cuts off the righttail AUC: Pr( Z > z * ) = . Then, reject H : = when the test statistic z = X / n > z * or equivalently when p < . Is p < ? Is z > z * ? D is trib u tio n o f te s t s ta t. z z x D is trib u tio n o f te s t s ta t. z z p  v a lu e D is trib u tio n s u n d e r H : = fo r te s tin g H a : Mugglin and Eberly PubH 6450 Fall 2011 Part 11 4 / 21 Review Revisiting Important Concepts Extending the Ideas Behind Hypothesis Tests for Metabolic changes due to HAART (revisited) Scientific question of interest: Do HIV+ patients who start a treatment regimen including a protease inhibitor (PI) see an increase in their BMI?...
View
Full
Document
This note was uploaded on 11/21/2011 for the course PUBH 6450 taught by Professor Andymugglin during the Fall '10 term at Minnesota.
 Fall '10
 AndyMugglin

Click to edit the document details