Lecture 15 (7.9)

# Lecture 15 (7.9) - Lecture 15 page 1 Statistics 371-001 Sp...

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

Statistics 371-001, Sp 09 Lecture #152 123 Mar 09 Chapter 7. Comparison of Two Independent Samples (concluded) 7.8 PLANNING FOR ADEQUATE POWER. Power depends on α , n , and ( μ 1 μ 2 ) in interdependent ways. Table 5. 7.9 STUDENT’S t : CONDITIONS AND SUMMARY 7.10 MORE ON PRINCIPLES OF TESTING HYPOTHESES 1. Conditions of the design of the study a. Random sampling from respective populations. b. Populations must be large. c. Observations within each population must be independent. d. Samples must be independent of each other. 2. Conditions on the form of the population distributions. a. If sample sizes are small, population distributions must be approximately normal. b. If samples sizes are large, be aware that one or two extreme outliers can have a great effect on results. ( n s = 20) 1a-c. Verified through analysis of experimental design and structure of sample. 1d. Samples must not be paired or dependent – more later. 2. Graph samples. Transform data. . t -test is robust. Violations May inflate probability of Type I error by inaccurately increasing t s . t -test may be inappropriate for the design and reduce power. 7.11 WILCOXON-MANN-WHITNEY TEST Similar to t -test for two independent samples: Two independent samples; independent observations within samples. Random sampling.

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.

{[ snackBarMessage ]}

### Page1 / 4

Lecture 15 (7.9) - Lecture 15 page 1 Statistics 371-001 Sp...

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

View Full Document
Ask a homework question - tutors are online