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: Solution to Homework #3 Stat c151/c225 Winter 2011 4.6 Because any nonzero estimated effects are significant the optimal setting corresponds to run 6 with percentage of noncracked springs, the response Y=90. In the onefactoratatime approach, suppose we start at run 1. The Y is 67. Now change only oil temperature. From run 5 we find Y=59, so the best level of oil temperature is 70. Now keeping oil temperature at 70, change percentage of carbon. From run no. 3, we see that Y=61, so the best level of percentage of carbon is 0.50. Then keeping oil temperature at 70 and percentage of carbon at 0.50, change the steel temperature. From run 2, Y=79. So the best level of steel temperature is 1600. Thus the best setting from the onefactoratatime approach is run 2 with Y=79. Thus we miss the optimal setting. 4.10 This experiment has 3 factors, each at 3 levels. For two 3level factors, we can break the 2 factor interaction into four components (for example, linearbylinear, linearbyquadratic, quadratic...
View
Full
Document
This note was uploaded on 03/03/2011 for the course CEE 330 taught by Professor Schneider during the Fall '10 term at Wisconsin.
 Fall '10
 SCHNEIDER

Click to edit the document details