Question 882579: Nondestructive evaluation is a method that is used to
describe the properties of components or materials without
causing any permanent physical change to the units. It includes
the determination of properties of materials and the
classification of flaws by size, shape, type, and location. This
method is most effective for detecting surface flaws and characterizing
surface properties of electrically conductive materials.
Data were collected that classified each component as
having a flaw or not, based on manual inspection and operator
judgment, and the data also reported the size of the crack
in the material. Do the components classified as unflawed
have a smaller mean crack size than components classified as
flawed? The results in terms of crack size (in inches) are
stored in . (Data extracted from B. D. Olin and W. Q.
Meeker, “Applications of Statistical Methods to Nondestructive
Evaluation,” Technometrics, 38, 1996, p. 101.)
a. Assuming that the population variances are equal, is
there evidence that the mean crack size is smaller for the
unflawed specimens than for the flawed specimens? (Use
)
b. Repeat (a), assuming that the population variances are
not equal.
c. Compare the results of (a) and (b).
Type Crack size
0 0.003
0 0.004
0 0.012
0 0.014
0 0.021
0 0.023
0 0.024
0 0.030
0 0.034
0 0.041
0 0.041
0 0.042
0 0.043
0 0.045
0 0.057
0 0.063
0 0.074
0 0.076
1 0.022
1 0.026
1 0.026
1 0.030
1 0.031
1 0.034
1 0.042
1 0.043
1 0.044
1 0.046
1 0.046
1 0.052
1 0.055
1 0.058
1 0.060
1 0.060
1 0.070
1 0.071
1 0.073
1 0.073
1 0.078
1 0.079
1 0.079
1 0.083
1 0.090
1 0.095
1 0.095
1 0.096
1 0.100
1 0.102
1 0.103
1 0.105
1 0.114
1 0.119
1 0.120
1 0.130
1 0.160
1 0.306
1 0.328
1 0.440
Answer by lenjinx(1)   (Show Source):
|
|
|
