7. Product and Process Comparisons  Detailed Table of Contents [7.]
 Introduction [7.1.]
 What is the scope? [7.1.1.]
 What assumptions are typically made? [7.1.2.]
 What are statistical tests? [7.1.3.]
 Critical values and p values [7.1.3.1.]
 What are confidence intervals? [7.1.4.]
 What is the relationship between a test and a confidence interval? [7.1.5.]
 What are outliers in the data? [7.1.6.]
 What are trends in sequential process or product data? [7.1.7.]
 Comparisons based on data from one process [7.2.]
 Do the observations come from a particular distribution? [7.2.1.]
 Chisquare goodnessoffit test [7.2.1.1.]
 Kolmogorov Smirnov test [7.2.1.2.]
 AndersonDarling and ShapiroWilk tests [7.2.1.3.]
 Are the data consistent with the assumed process mean? [7.2.2.]
 Confidence interval approach [7.2.2.1.]
 Sample sizes required [7.2.2.2.]
 Are the data consistent with a nominal standard deviation? [7.2.3.]
 Confidence interval approach [7.2.3.1.]
 Sample sizes required [7.2.3.2.]
 Does the proportion of defectives meet requirements? [7.2.4.]
 Confidence intervals [7.2.4.1.]
 Sample sizes required [7.2.4.2.]
 Does the defect density meet requirements? [7.2.5.]
 What intervals contain a fixed percentage of the population values? [7.2.6.]
 Approximate intervals that contain most of the population values [7.2.6.1.]
 Percentiles [7.2.6.2.]
 Tolerance intervals for a normal distribution [7.2.6.3.]
 Tolerance intervals based on the largest and smallest observations [7.2.6.4.]
 Comparisons based on data from two processes [7.3.]
 Do two processes have the same mean? [7.3.1.]
 Analysis of paired observations [7.3.1.1.]
 Confidence intervals for differences between means [7.3.1.2.]
 Do two processes have the same standard deviation? [7.3.2.]
 How can we determine whether two processes produce the same proportion of
defectives? [7.3.3.]
 Assuming the observations are failure times, are the failure rates (or Mean Times To Failure) for two distributions the same? [7.3.4.]
 Do two arbitrary processes have the same central tendency? [7.3.5.]
 Comparisons based on data from more than two processes [7.4.]
 How can we compare several populations with unknown distributions (the KruskalWallis test)? [7.4.1.]
 Assuming the observations are normal, do the processes
have the same variance? [7.4.2.]
 Are the means equal? [7.4.3.]
 1Way ANOVA overview [7.4.3.1.]
 The 1way ANOVA model and assumptions [7.4.3.2.]
 The ANOVA table and tests of hypotheses about means [7.4.3.3.]
 1Way ANOVA calculations [7.4.3.4.]
 Confidence intervals for the difference of treatment means [7.4.3.5.]
 Assessing the response from any factor combination [7.4.3.6.]
 The twoway ANOVA [7.4.3.7.]
 Models and calculations for the twoway ANOVA [7.4.3.8.]
 What are variance components? [7.4.4.]
 How can we compare the results of
classifying according to several categories? [7.4.5.]
 Do all the processes have the same proportion of defects? [7.4.6.]
 How can we make multiple comparisons? [7.4.7.]
 Tukey's method [7.4.7.1.]
 Scheffe's method [7.4.7.2.]
 Bonferroni's method [7.4.7.3.]
 Comparing multiple proportions: The
Marascuillo procedure [7.4.7.4.]
 References [7.5.]
