This preview has intentionally blurred sections. Sign up to view the full version.View Full Document
Unformatted text preview: STATISTICS 500 – Fall 2009 Homework 4 - handed out Friday, September 18, 2009 DUE DATE: on campus Friday, 25 Sept 2009, in lecture (11 am) or by e-mailto Chuanlong, [email protected], no later than noon. off campus Monday, 28 Sept 2009, by 4 pm to Nicole Rembert, email: [email protected] or FAX: 515-294-4040 (please include cover page with Stat 500 / Nicole Rembert). 1. The following is based on an experiment comparing diet plans for dogs. Individual dogs are randomly assigned to a diet plan. At the end of one month the investigators measure blood urea concentration, in mg/dL. They use ANOVA to analyze the data. A portion of the ANOVA table is provided below. Source d.f. SS MS Treatment 3 Error 20 441.35 Total 2714.15 Note: This problem requires hand calculation throughout. (a) Fill in the rest of the ANOVA table from the information provided. (b) How many diet plans are being compared? (c) Assume all groups have the same sample size. How many observations in each treatment group? (d) Test H0: all means are equal. Report the F statistic, p-value, and state a reasonable conclusion. 2. For each of the following studies, indicate whether the specified factor(s) should be considered fixed or random and explain your choice (1 sentence). (a) A study of student achievement in Los Angeles High Schools. 10 high schools are randomly chosen from the list of high schools in LA. (I don’t know the actual number, but there must be 100+ high schools in the LA school district). 40 seniors are randomly chosen from each school and given an achievement test. The aim is to estimate the average achievement score for the school district. Schools should be treated as (Fixed? Random?). (b) A second study of student achievement in LA. You are a principal at high school A. You want to know if your school has higher achievement than any other school. You get permission to survey 9 additional schools. Again, the achievement test is given to 40 students per school. The aim is to estimate the 9 differences between school A and each of the other 9 schools. Schools should be treated as ??....
View Full Document
- Fall '08
- Statistics, High Schools, model comparison approach