Homework07Solns

# Homework07Solns - Stat 512 2 Solutions to Homework#7 Dr...

This preview shows pages 1–3. Sign up to view the full content.

Stat 512 – 2 Solutions to Homework #7 Dr. Simonsen Due October 19, 2005 by 4:30pm. 1. For this problem, the idea is to demonstrate the similarity between regression with dummy variables and ANOVA. To do this run the following SAS code. (If you download this assignment from the Homework page of the class website you can copy and paste the code into SAS.) (a) Compare the ANOVA table and parameter results from the GLM analysis and Parameterization #1. What do the coefficients associated with X 1 and X 2 (i.e. b 1 and b 2 ) estimate in terms of treatment means? What constraint system does this parameterization correspond to? The ANOVA tables from the two analyses are identical. The parameter estimates , , and ˆ μ 1 ˆ τ 2 ˆ τ from the GLM analysis are the same as the parameter estimates b 0 , b 1 , and b 2 from the regression model. The fourth parameter estimate which is set to zero in the GLM analysis does not appear in the regression analysis, since it is assumed equal to zero in that model. Parameterization #1 sets 3 ˆ τ μ 1 = β 0 + β 1 = μ + τ 1 , μ 2 = β 0 + β 2 = μ + τ 2 , and μ 3 = β 0 = μ . This system of equations can be solved for the β ’s to obtain β 0 = μ = μ 3 , β 1 = τ 1 = μ 1 μ 3 , and β 2 = τ 2 = μ 2 μ 3 . The coefficient associated with X is b 1 = 1 ˆ τ , which thus is an estimate for μ 1 μ 3 . The coefficient associated with X 2 is b 2 = , which thus is an estimate for μ 2 ˆ τ 2 μ 3 . This corresponds to the constraint system τ 3 = 0. The GLM Procedure Dependent Variable: response Sum of Source DF Squares Mean Square F Value Pr > F Model 2 38.88888889 19.44444444 15.91 0.0040 Error 6 7.33333333 1.22222222 Corrected Total 8 46.22222222 Standard Parameter Estimate Error t Value Pr > |t| Intercept 26.66666667 B 0.63828474 41.78 <.0001 trt 1 -5.00000000 B 0.90267093 -5.54 0.0015 trt 2 -1.66666667 B 0.90267093 -1.85 0.1144 trt 3 0.00000000 B . . . The REG Procedure Model: MODEL1 Dependent Variable: response Analysis of Variance Sum of Mean Source DF Squares Square F Value Pr > F Model 2 38.88889 19.44444 15.91 0.0040

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

View Full Document
Error 6 7.33333 1.22222 Corrected Total 8 46.22222 Parameter Estimates Parameter Standard Variable DF Estimate Error t Value Pr > |t| Intercept 1 26.66667 0.63828 41.78 <.0001 x1 1 -5.00000 0.90267 -5.54 0.0015 x2 1 -1.66667 0.90267 -1.85 0.1144 (b) Compare the ANOVA table and parameter results from the GLM analysis and Parameterization #2. What do the coefficients associated with X 1 and X 2 (i.e. b
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

### What students are saying

• As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

Kiran Temple University Fox School of Business ‘17, Course Hero Intern

• I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

Dana University of Pennsylvania ‘17, Course Hero Intern

• The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

Jill Tulane University ‘16, Course Hero Intern