Lecture03

# Lecture03 - Applied Nonparametrics STA 4502/5507 Yiyuan She...

This preview shows pages 1–14. Sign up to view the full content.

Applied Nonparametrics STA 4502/5507 Yiyuan She Department of Statistics, Florida State University Fall 2009

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

View Full Document
Possible Course Flow Estimating success probabilities Single location: estimates, tests, intervals Two locations: testing, estimating di±erences between locations Scale comparisons Multiple locations and factors Independence Nonparametric regression Other topics . ..
Location Compare two population centers (paired replicates data) Perhaps before and after of one population One population, where is center? Will use signs and ranks of data

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

View Full Document
Paired Replicates Assumptions Data comes in pairs ( X i ; Y i ), i = 1 ; 2 ; : : : ; n Focus on Z i = Y i ± X i Z i are (mutually) independent Z i come from continuous populations (not necessarily the same) Z i symmetric about ± : F i ( ± + t ) + F i ( ± ± t ) = 1 for all t ; i ± : treatment e±ect
Wilcoxon Test Distribution-free ( X ; Y ) Some assumptions (pairs, symmetry, independence) Null: H 0 : ± = 0 No di±erence before and after

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

View Full Document
Wilcoxon Test Set i = 8 < : 1 ; Z i > 0 ; 0 ; Z i < 0 : Get ranks R i of j Z i j Test statistic is T + = n X i =1 R i i
Example Patient i X i Y i 1 1.83 0.878 2 0.50 0.647 3 1.62 0.598 4 2.48 2.05 5 1.68 1.06 6 1.88 1.29 7 1.55 1.06 8 3.06 3.14 9 1.30 1.29

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

View Full Document
Example i Z i j Z i j R i i R i i 1 -.952 .952 8 0 0 2 .147 .147 3 1 3 3 -1.022 1.022 9 0 0 4 -.430 .430 4 0 0 5 -.620 .620 7 0 0 6 -.590 .590 6 0 0 7 -.490 .490 5 0 0 8 .080 080 2 1 2 9 -.010 .010 1 0 0
Wilcoxon Test Suppose ± > 0 Should be more positive Z i s Should be large (higher ranks) T + will be bigger Reject ± = 0 when T + big

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

View Full Document
Wilcoxon Statistic Under H o , 0 ± T + ± n ( n +1) 2 E ( T + ) = n ( n +1) 4 var ( T + ) = n ( n +1)(2 n +1) 24 Symmetry: T + is symmetric about ET + T + d = P n 1 ib i , where b i i : i : d : ² Bernoulli(1 = 2) Distribution available; see Table A.4
Wilcoxon Test One-tail alternative H 1 : ± > 0 Reject H 0 if T + ± t ± t ± : Table A.4 in NSM or wilcox.test in R

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

View Full Document
Wilcoxon Test One-tail alternative H 1 : ± < 0 Reject H 0 if T + ± n ( n +1) 2 ² t ± Symmetry when H 0 true Center of T + is n ( n +1) 4 Two-tail alternative H 1 : ± 6 = 0 Reject H 0 if T + ± n ( n +1) 2 ² t ±= 2 or T + ³ t ±= 2
Wilcoxon Test Large sample approximation E ( T + ) = n ( n +1) 4 var ( T + ) = n ( n +1)(2 n +1) 24 T ± = T + ² E ( T + ) p var ( T + ) _ ± N (0 ; 1) CLT: Is T + the sum of i.i.d. random variables? T

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.

## This note was uploaded on 12/16/2011 for the course STAT 5407 taught by Professor Frade during the Fall '09 term at FSU.

### Page1 / 52

Lecture03 - Applied Nonparametrics STA 4502/5507 Yiyuan She...

This preview shows document pages 1 - 14. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online