This preview shows pages 1–2. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.View Full Document
Unformatted text preview: Stat 462, Spring 2008 Homework 4 Solution key Due February 29, 2008 Prepared by: Esra Kurum 2.17 (5 points) The α level used by the analyst was greater than 0.033. If α level had been 0.01, the appropriate conclusion would have been to accept the Ho. 2.18 (5 points) The t-test may be calculated as a one-sided or a two-sided test, but the F-test is only two-sided. 2.22(20 points) It is possible that for a complete set of 30 cases the R 2 won’t be zero; since if the 20 cases that we didn’t consider while first estimating R 2 falls on the regression line they will decrease SSE and increase the value of R 2 . It is possible that for a complete set of 30 cases the R 2 being zero; but not being zero for the first 10 cases. For instance for Y=X 2 , R 2 can be zero for the 30 cases but for the first part of the curve R 2 is not equal to zero.-15-10-5 5 10 15 50 100 150 200 x x^2 for the first 10 cases Rsquare is not zero 2.23(25 points- a 4 points; b, c, d 5 points each; e and f 3 points each) a) Analysis of Variance Table Source DF SS MS F P Regression 1 3.5878 3.5878 9.24 0.003 Residual Error 118 45.8176 0.3883 Stat 462, Spring 2008...
View Full Document
This note was uploaded on 03/17/2008 for the course STAT 462 taught by Professor Senturk,damla during the Spring '08 term at Penn State.
- Spring '08
- Regression Analysis