This preview shows pages 1–3. 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: 1 Homework 10 (9 points) due Dec. 2 (2.5 pts.) 11.12 (p.507) [Please use two different hypotheses tests.] Exercise 23 (Section 3.3) gave SAS output from a regression of attenuation on fracture strength. a) Does the simple linear regression model appear to specific a useful relationship between these two variables? State the relevant hypothesis and carry out a test using two different hypothesis test. using : 1. Let be the true mean slope of attenuation vs. fracture strength. 2. H : = 0 H a : 0 3. = 0.05 4. ? = ? ? ? = 0.014711 0.00143620 = 10.243 ( ? ? h ? ?? ? ? ) 5. SAS = 0.0001 df = 12, P = 2P(t > 10.243) < 0.002 (not required) 6. Reject H because 0.0001 0.05 7. This data does give strong support (P = 0.0001) to the claim that there is a linear relationship between attenuation and fracture strength. using : 1. Let be the true mean correlation coefficient of attenuation vs. fracture strength. 2. H : = 0 H a : 0 3. = 0.05 4. ? = ? 2 1 2 = ( 0.8974 ) 12 1 0.8974 = 10.243 ( ? ? h ? ?? ? ? ) 5. SAS = 0.0001 df = 12, P = 2P(t > 10.243) < 0.002 (not required) 6. Reject H because 0.0001 0.05 7. This data does give strong support (P = 0.0001) to the claim that there is a linear relationship between attenuation and fracture strength. 2 using F test 1. Let be the true mean slope of attenuation vs. fracture strength. 2. H : = 0 H a : 0 3. = 0.05 4. ? = ? = 2.29469 0.02187 = 104.917 ( ? ? h ? ) 5. SAS = 0.0001 df 1 = 1 df 2 = 12, P = P(F > 104) < P(F > 9.33) = 0.001 (not required) 6. Reject H because 0.0001 0.05 7. This data does give strong support (P = 0.0001) to the claim that there is a linear relationship between attenuation and fracture strength....
View
Full
Document
 Spring '08
 Staff
 Statistics, Linear Regression

Click to edit the document details