511_Chap4 - Alternatives to the t-Tools Stat 511 Chap 4...

Info iconThis preview shows pages 1–10. Sign up to view the full content.

View Full Document Right Arrow Icon
Stat 511 Chap 4 1 Alternatives to the t-Tools Stat 511 Chap 4
Background image of page 1

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

View Full DocumentRight Arrow Icon
Stat 511 Chap 4 2 Case Study 1: O-Ring Failures
Background image of page 2
Stat 511 Chap 4 3 Case Study 1: O-Ring Failures observational study highly unbalanced far from normal apparently equal standard deviations – larger sample size is associated with smaller standard deviation 1 2 Count 1 2 3 4 5 10 15 0 1 2 3
Background image of page 3

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

View Full DocumentRight Arrow Icon
Stat 511 Chap 4 4 Case Study 2: Cognitive Load randomized experiment students not randomly selected highly skewed distributions ‘censored’ data Stem Leaf 21 0 20 6 19 7 18 3 17 16 15 5 14 8 13 2 12 11 10 9 8 00 7 0357 6 8 Count 1 1 1 1 1 1 1 2 4 1 Stem Leaf 30 00000 29 28 27 26 5 25 24 2 23 22 8 21 20 19 18 17 7 16 1 15 0 14 6 13 09 Count 5 1 1 1 1 1 1 1 2 50 100 150 200 250 300 TIME CONVENTIONAL MODIFIED TREATMT
Background image of page 4
Stat 511 Chap 4 5 Drastic Violations of t-test Assumptions Example -- Space Shuttle O- Ring data What assumptions are violated? normality (drastically violated) equal standard deviations? Will the log transformation help? 1 2 Count 1 2 3 4 5 10 15 0 1 2 3
Background image of page 5

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

View Full DocumentRight Arrow Icon
Stat 511 Chap 4 6 Drastic Violations of t-test Assumptions Cognitive Load data What assumptions are violated? data are censored normality Will the log transformation help? St em Leaf 21 0 20 6 19 7 18 3 17 16 15 5 14 8 13 2 12 11 10 9 8 00 7 0357 6 8 Count 1 1 1 1 1 1 1 2 4 1 Stem Leaf 30 00000 29 28 27 26 5 25 24 2 23 22 8 21 20 19 18 17 7 16 1 15 0 14 6 13 09 Count 5 1 1 1 1 1 1 1 2
Background image of page 6
Stat 511 Chap 4 7 The Rank-Sum Test The Rank-Sum has several names Wilcoxon Rank-Sum Test Mann-Whitney U Developed in the 1940’s by Frank Wilcoxon – a chemist, not a statistician
Background image of page 7

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

View Full DocumentRight Arrow Icon
Stat 511 Chap 4 8 The Rank-Sum Test a nonparametric or distribution free tool no specific distributional assumptions (like normality) required tests the null hypothesis of identical population medians an implied assumption is that the populations have the same spread
Background image of page 8
9 The Rank-Sum Test Performs nearly as well as the two-sample t- test when the data are normal and CONSIDERABLY BETTER when there are extreme outliers. resistant (because it is based
Background image of page 9

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

View Full DocumentRight Arrow Icon
Image of page 10
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 32

511_Chap4 - Alternatives to the t-Tools Stat 511 Chap 4...

This preview shows document pages 1 - 10. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online