lecture04

lecture04 - Possible Course Flow Estimating success...

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

View Full Document Right Arrow Icon
Possible Course Flow Estimating success probabilities Single location: estimates, tests, intervals Two locations: testing, estimating differences between locations Scale comparisons Multiple locations and factors Independence Nonparametric regression Other topics . ..
Background image of page 1

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

View Full DocumentRight Arrow Icon
Location Compare two population centers Location differences (only) Now, two distinct populations (data not paired)
Background image of page 2
Assumptions X i , i = 1 , 2 , . . . , m iid F (population 1) Y i , i = 1 , 2 , . . . , n iid G (population 2) N = m + n observations X i ’s and Y i ’s are independent Continuous populations
Background image of page 3

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

View Full DocumentRight Arrow Icon
Wilcoxon (Mann-Whitney) Test Distribution-free Some assumptions (continuous, iid) Null: H 0 : F ( t ) = G ( t ) for all t Same distribution
Background image of page 4
Wilcoxon (Mann-Whitney) Test Usually interested in a shift of one distribution with respect to the other X F . Let X 0 = X + Δ. What is the distribution of X 0 ? Location shift model ( assumption ): G ( t ) = F ( t - Δ) for all t Or Y d = X + Δ Δ is location shift or treatment effect If E ( X ) and E ( Y ) exist Δ = E ( Y ) - E ( X ) H 0 : G ( t ) = F ( t ) vs. H 1 : G ( t ) = F ( t - Δ) with Δ >, <, 6 = 0. Or H 0 : Δ = 0 vs. H 1 : Δ >, <, 6 = 0
Background image of page 5

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

View Full DocumentRight Arrow Icon
Wilcoxon (Mann-Whitney) Test Rank the N (= m + n ) combined samples Denote the ranks of Y within this ranking as S i W = n j =1 S j = n j =1 rank ( Y j ) Rank-sum test
Background image of page 6
One-tail alternative H 1 : Δ > 0 Reject H 0 if W w α Table A.6 Assumes Y is the smaller sample size ( n m ) n ( n + 1)
Background image of page 7

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

View Full DocumentRight Arrow Icon
Image of page 8
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 / 30

lecture04 - Possible Course Flow Estimating success...

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

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