LectureNov12

# LectureNov12 - BME 423 Lecture Notes Nov 12 2008 Methods...

This preview shows pages 1–11. Sign up to view the full content.

Methods Based on Ranks – Nonparameteric Methods BME 423 Lecture Notes - Nov. 12, 2008 I Parametric versus Nonparameteric Methods II. Mann-Whitney Rank-Sum – Two Different Groups A. Idea B. Mann-Whitney Test C. Example III. Wilcoxon Signed-Rank – Same Subject, Two Treatments A. Idea B. Wilcoxon Test C. Example Glantz Chapt. 10, pp 363-385

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
Normal or Gaussian Density f ( x ) x μ σ 2 ~( , ) XN μσ () 2 2 1 exp 2 2 x x f μ σ σπ ⎛⎞ −− ⎜⎟ ⎝⎠ =

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

View Full Document
II. Mann-Whitney Rank-Sum – Two Different Groups A. Idea Make inferences based on Rank T – Sum of Ranks in Smaller Group will be used as the Test Statistics 12 0: H μ =
Is T=9 sufficiently extreme to justify rejecting the hypothesis that the drug had no effect? (35 possibilities)

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

View Full Document
Distribution of T under the Null Hypothesis

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

View Full Document
Procedure 1. Rank all observations in ascending order regardless of group (ties ). 2. Compute T – sum of ranks in smaller group. 3. Comparer T to its critical values a. use T statistic table b. use Normal distribution pdf of T 8 B N 8 B N > 2 (, ) TT N μ σ
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

### Page1 / 19

LectureNov12 - BME 423 Lecture Notes Nov 12 2008 Methods...

This preview shows document pages 1 - 11. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online