# 2-17 - a false Bonferroni Correction Bonferroni ∝ of...

This preview shows pages 1–2. Sign up to view the full content.

2 17 2011 Case Study 0502 Multiple means – f-test – ANOVA Full model – everything is there Reduced model – group things together that answer another question FULL MODEL: Separate Means model – case 0502, seven total groups REDUCED MODEL: Two Groups (Spock vs. others) How do we group? It depends on the question. NULL Hypothesis: H 0 : Reduced= Full H A : Reduced is too much F = ∆SSE∆dfMSEfull Wilcoxon Rank Sum test – similar to overall F-test (the f-statistic) Compare Means – Each Pair Student’s t Potential problem with all the means: the Alpha = 0.05: 5% of the significant things will not be significant. 1/20 chance of finding

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.

Unformatted text preview: a false Bonferroni Correction: Bonferroni: ∝# of comparisons = . 0 0521 = 0.0023 NOTE: Most common mistake: Not correct for multiple comparisons. Tukey: All pairs, means comparison Best: Dunnett’s: Control, difference from a control group Example: Lowest A B C D E highest A = B, B = C, A ≠ C C = D = E Homework 6 5.23 analyze FIT y by x. All the means are the same because the F Ratio is significant. [Following is not needed] All possible differences. Tukey. LSD: Stands for least significant difference. Remember: The student test doesn’t correct for the alpha, where as the tukey test does. A...
View Full Document

## This note was uploaded on 10/03/2011 for the course STAT 511 taught by Professor Eggett,d during the Winter '08 term at BYU.

### Page1 / 2

2-17 - a false Bonferroni Correction Bonferroni ∝ of...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online