# hw6 - What set of operating conditions would you...

This preview shows page 1. Sign up to view the full content.

Stat 201A HW6: Due Wednesday, November 10, 2010 (in class) 1. An experiment was run in a wave soldering process. There are ﬁve controllable variables and three noise variables. The response variable is the number of solder defects per million opportunities. The experimental design employed was the crossed array shown below [see solder.dat]. Outer Array F - 1 1 1 - 1 Inner Array G - 1 1 - 1 1 A B C D E H - 1 - 1 1 1 1 1 1 - 1 - 1 194 197 193 275 1 1 - 1 1 1 136 136 132 136 1 - 1 1 - 1 1 185 261 264 264 1 - 1 - 1 1 - 1 47 125 127 42 - 1 1 1 1 - 1 295 216 204 293 - 1 1 - 1 - 1 1 234 159 231 157 - 1 - 1 1 1 1 328 326 247 322 - 1 - 1 - 1 - 1 - 1 186 187 105 104 (a) What types of designs were used for the inner and outer arrays? What are the resolu- tions? (b) Write down the alias structure for the inner array (ignoring 3-factor or higher-order interactions). (c) Develop models for the mean and variance of solder defects.
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: What set of operating conditions would you recommend? (d) Redo the analysis using the response modeling approach. What set of operating condi-tions would you recommend? [For your convenience, use solder2.dat.] (e) Find a combined array design for this experiment that requires fewer runs. 2. Show that E ( s 2 ) = σ 2 in simple random sampling (without replacement), where s 2 = 1 n-1 ∑ i ∈ s ( y i-¯ y ) 2 and σ 2 = 1 N-1 ∑ N i =1 ( y i-μ ) 2 . Instruction: Write down your answers to the questions and attach only necessary computer outputs and graphs. 1...
View Full Document

{[ snackBarMessage ]}

Ask a homework question - tutors are online