Chapter 11

# Chapter 11 - Review Quantitative Data Analyses so far One...

This preview shows pages 1–15. Sign up to view the full content.

Review: Quantitative Data Analyses so far

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

View Full Document
σ 2 =? p = ? µ = ? σ known σ not known z -test t -test z test chi square test One population tests µ 1 = µ 2 Dependent Paired Blocked (2trts) paired t -test Independent Unpaired CRD (2trts) 2 sample t -test 2 populations test
Quantitative Bivariate Data Correlation Regression • ρ = 0 β 1 = 0 t-test for correlation t-test for regression What about Qualitative Data?

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

View Full Document
Chapter 11 Applications of Chi Square
Chi-Square Statistic Qualitative Data Have Observed numbers = Counts Ex: The number of men vs. women that smoke or don’t smoke Three Types of Chi Square Tests 1) Goodness of Fit Tests 2) Tests of Independence 3) Tests of Homogeneity

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

View Full Document
All 3 tests use same statistic equation Different equation (from Chapter 5) but same Table 8 O = Observed Number E = Expected Number 1 tailed tests: interest is the right tail = big χ 2 * values What does a small χ 2 * value mean? - = E E O 2 2 ) ( * χ
- = E E O 2 2 ) ( * χ 0 0

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

View Full Document
Chi Square Tests 1) Goodness of Fit Tests Book calls multinomial experiments 2) Tests of Independence 3) Tests of Homogeneity (treatment effects) Qualitative Data (observed #s) 1 qualitative variable GOF test 2 qualitative variables Test of Independence Test of Homogeneity
Goodness of Fit Tests Flashback: Do data fit binomial distribution? Key Points: You have a single list of observed numbers in categories Question drives hypotheses H o : Data follow expected distribution H a : Data don’t follow expected distribution. Hypotheses often verbal statements

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

View Full Document
Do car crashes occur on different days with the same frequency? Sample from Maryland in May 2004 Example Test the claim that accidents occur with equal frequency Use α = 0.05 What is the expected # for each square given the question ? Day Sun Mon Tue Wed Thur Fri Sat # Fatalities 31 20 20 22 22 29 36
1 . State your question (ID population) Are fatal auto accidents equally likely on all days in Maryland? 2. State your H o and H a (define symbols) H o : fatal auto accidents in Maryland are equally likely on all days H a : fatal auto accidents in Maryland are not equally likely on all days

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

View Full Document
Calculate test statistic need to calculate expected values expected #s based on null hypothesis here: accidents equally likely on all days so: take the total # of accidents and divide by 7 to get the expected # for each day =180 ∕ 7 = 25.7 -Chi Square tests do have 1 Assumption: All EXPECTED values > 5 25.7 bigger than 5 so that assumption okay
Day Sun Mon Tue Wed Thu Fri Sat # fatalities Observed 31 20 20 22 22 29 36 # fatalities Expected 25.7 25.7 25.7 25.7 25.7 25.7 25.7 - = E E O 2 2 ) ( * χ

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

View Full Document
χ 2* = (31-25.7) 2 / 25.7
This is the end of the preview. Sign up to access the rest of the document.

## This note was uploaded on 04/05/2012 for the course BIOM 301 taught by Professor Staff during the Winter '08 term at Maryland.

### Page1 / 46

Chapter 11 - Review Quantitative Data Analyses so far One...

This preview shows document pages 1 - 15. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online