Page 593 - Design for Six Sigma a Roadmap for Product Development
P. 593
Design Optimization: Advanced Taguchi Robust Parameter Design 549
Output response
y
Linear regression
line
Scatter of responses due
to noise factors
Signal factor
M
M 1 M 2 M k
Figure 15.9 Typical scatterplot for a complete inner-array run.
TABLE 15.2 Complete Data Set for Each Inner-Array Run
Signal factor levels
Noise factor levels M 1 M 2 … M k
N1 y 11 y 12 … y 1k
N2 y 21 y 22 … y 2k
Nm y m1 y m2 y mk
By fitting a linear regression equation using the standard procedure,
we obtain
y β 0 β 1 M ε where Var(ε) 2 (15.2)
where
k m
M j (y ij y … )
j 1 i 1
^
β (15.3)
k
1
m
(M j M ) 2
j 1
^ ^
β 0 y … β 1 M (15.4)
