# Six Sigma with R: Statistical Engineering for Process Improvement (Use R!)

## Emilio L. Cano, Andrés Redchuk

Language: English

Pages: 284

ISBN: 1461436516

Format: PDF / Kindle (mobi) / ePub

Six Sigma has developed over the last twenty years into a powerful quality management tool. Taking a purely applied perspective, the book explains this statistical device through a variety of comprehensible examples that are accessible to a range of readers.

Piping Handbook

Rethinking Western Approaches to Counterinsurgency: Lessons From Post-Colonial Conflict (Studies in Insurgency, Counterinsurgency and National Security)

The Bullying Workbook for Teens: Activities to Help You Deal with Social Aggression and Cyberbullying

La guía de salud: consejos y respuestas para la mujer latina

list(c("Waiter","C"), c("queue", "N")) > > > > > feat <- list() feat[[1]] <- list("Density", "toughness", "thickness") feat[[2]] <- list("Diameter", "Weight", "thickness") feat[[3]] <- list("temperature", "tenderness", "taste") feat[[4]] <- list("temperature", "taste", "tenderness", "weight", "radius", "time") Now we have all the data stored in variables. 58 3 Process Mapping with R Table 3.1 Arguments of ss.pMap function Argument Description steps Vector of characters with names of “n”

expressions (also known as model formulae) to call the function. Type ?formula to learn more about model formulae with R. Example 8.5 (Printer cartridge (cont.)). In the ss.data.pc data set, we have two continuous variables: pc.volume and pc.density. If we want to check whether the density and the volume are related, the fir t thing we have to do is generate a scatterplot to f nd patterns for this relation. We use the following code to produce the scatterplot in Fig. 8.9. > plot(pc.volume ~

res Min. : 1.000 1st Qu.: 6.000 Median : 7.000 Mean : 6.667 3rd Qu.: 8.000 Max. :10.000 For a factor (qualitative variable), what you get is the frequency of each level. 9.2 Descriptive 149 Long Term / Short Term Variability 54 Variable 52 50 48 46 44 0 20 40 60 80 100 120 Time Fig. 9.1 Long-term and short-term variability. In the short term, the variability is constant over time. In the long term, there are ups and downs that reflec assignable causes that should be identif

lines(density(ss.data.strings\$len), lwd=2) We can confir normality using the quantile–quantile plot (Fig. 9.4), plotted using the following code: > qqnorm(ss.data.strings\$len, pch = 16) > qqline(ss.data.strings\$len) If we assume that the length of the strings is normal with mean 950 mm and standard deviation 0.25,5 the probability of findin a string shorter than 949.5 mm is 5 We assume that these are the values define in our manufacturing process. 156 9 Statistics and Probability with R

. . 93 6.3.2 Measuring the Effect . . . . . . . . . . . . . . . . . . .. . . . . . . . . . . . . . . . . . . . 95 6.3.3 Building a Pareto Chart . . . . . . . . . . . . . . . .. . . . . . . . . . . . . . . . . . . . 96 6.4 Pareto Charts in R .. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .. . . . . . . . . . . . . . . . . . . . 96 6.5 Other Uses of the Pareto Chart . . . . . . . . . . . . . . . . . .. . . . . . . . . . . . . . . . . . . . 99 6.6 Summary and Further Reading . . . . .