midterm.00

# midterm.00 - problem(propose a diﬀerent design identify...

This preview shows page 1. Sign up to view the full content.

Midterm 1. For the following incomplete block design, determine whether the design is balanced. Find the interblock and intrablock estimators and their variances. Find the optimal weight π . Test for treatment eﬀects in the intrablock analysis. Block 1 2 3 4 5 A=25.2 A=24.5 A=21.3 A=26.5 B=18.4 B=18.3 B=17.7 B=23.1 C=17.6 C=22.5 C=23.5 C=22.6 D=25.7 D=22.4 D=31.3 D=31.0 E=25.9 E=20.7 E=26.7 E=28.0 2. A student and three friends want to test four diﬀerent routes for driving home. They decide that time of day, driver, and automobile may be important factors. Can you help them design a study to test for a route eﬀect taking all these blocking variables into consideration? What is a shortcoming of this study? How might you resolve this
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: problem (propose a diﬀerent design, identify the design and explain how you would test for a route eﬀect)? 3. Gulf, Florida and South Carolina red snapper are tested for population homogeneity. Suppose the variation in the number of times a short tandem repeat marker appears at a polymorpic site has standard deviation 10. How many ﬁsh from each population should be sampled if treatment eﬀect τ = (-4 , , 4) is to be detected with 80% power ( α = . 05)? Suppose we want to study treatment eﬀect τ = (-k, , k ) as a function of sample size. What sample sizes do we need to detect τ with 80% power for choices of k from 4 to 10? 1...
View Full Document

## This note was uploaded on 10/01/2009 for the course STAT stat706 taught by Professor Johnm.grego during the Spring '08 term at South Carolina.

Ask a homework question - tutors are online