Basic Analysis and Graphing - SAS

Chapter 2 Performing Univariate Analysis 85
Statistical Details for the Distribution Platform
Table 2.20 Descriptions of JMP Goodness of Fit Tests (Continued)
Distribution Parameters Goodness of Fit Test
LogNormal
μ and σ are known or
unknown
Kolmogorov's D
Weibull α and β known or unknown Cramér-von Mises W 2
Weibull with threshold α, β and θ known or unknown Cramér-von Mises W 2
Extreme Value α and β known or unknown Cramér-von Mises W 2
Exponential σ is known or unknown Kolmogorov's D
Gamma α and σ are known Cramér-von Mises W 2
either α or σ is unknown
(none)
Beta α and β are known Kolmogorov's D
Binomial
either α or β is unknown
ρ is known or unknown and n
is known
(none)
Kolmogorov's D (for n ≤ 30)
Pearson χ 2 (for n > 30)
Beta Binomial ρ and δ known or unknown Kolmogorov's D (for n ≤ 30)
Pearson χ 2 (for n > 30)
Poisson λ known or unknown Kolmogorov's D (for n ≤ 30)
Pearson χ 2 (for n > 30)
Gamma Poisson λ or σ known or unknown Kolmogorov's D (for n ≤ 30)
Pearson χ 2 (for n > 30)
a. For the three Johnson distributions and the Glog distribution, the data are transformed to Normal, then
the appropriate test of normality is performed.
Spec Limits
Writing T for the target, LSL, and USL for the lower and upper specification limits, and P α for the α*100 th
percentile, the generalized capability indices are as follows:
P 0.5
– LSL
C pl
= ------------------------------------
P 0.5
– P 0.00135
USL – P 0.5
C pu
= ------------------------------------
P 0.99865
– P 0.5
USL – LSL
C p
= -----------------------------------------------
P 0.99865
– P 0.00135