This document discusses using R software to support Six Sigma methodology. It introduces reproducible research approaches for statistical training, provides examples using Sweave documents to integrate R code and LaTeX, and outlines an EADAPU training program covering Six Sigma phases and tools. The document also describes using R for process mapping, loss function analysis, and measurement system analysis for quality improvement projects.
Six Sigma with R: A Guide to Implementation, Process Improvement, and Problem Solving
1. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
Seis Sigma con R
Emilio L. Cano
Departamento de Estad´ıstica e Investigaci´on Operativa
Universidad Rey Juan Carlos (Madrid)
December 5, 2012
E.T.S. Ingenieros Industriales
Universidad de Castilla-La Mancha
Seminario EIO UCLM 1/66
2. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
Contents
1 Statistical Training
Approaches
Examples
Application
2 Six Sigma with R
Six Sigma
R
Packages
Seminario EIO UCLM 2/66
3. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
Elements of Statistical Training
Seminario EIO UCLM 3/66
4. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
Copy-paste Approach
Inconsistencies
Errors
Out-of-date
non-reproducible
Painful changes
Seminario EIO UCLM 4/66
5. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
Reproducible Research Approach
Reproducible Research
The goal of reproducible research is to tie
specific instructions to data analysis and
experimental data so that scholarship can be
recreated, better understood and verified
Literate Programming
Literate programming is a methodology that
combines a programming language with a
documentation language
Seminario EIO UCLM 5/66
6. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
Reproducible Research
Workflow
Seminario EIO UCLM 6/66
7. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
Sweave Documents
Sweave
A Sweave document is a plain-text file which
merges LATEX code and R code. The R
function Sweave() converts the Sweave
document (*.Rnw) into a LATEX file (*.tex).
The code chunks are executed and the results
embedded into the LATEX file.
Seminario EIO UCLM 7/66
8. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
Sweave Example
documentclass [a4paper ]{ article}
usepackage{Sweave}
title{Design of Experiments}
author{EL Cano and JM Moguerza and A Rechuk}
begin{document}
maketitle
section{ Introduction }
Design of experiments is the most important took in the I
DMAIC cycle ldots.
<<>>=
library(SixSigma)
doe.model1 <- lm(score ~ flour + salt + bakPow +
flour * salt + flour * bakPow +
salt * bakPow + flour * salt * bakPow ,
data = ss.data.doe1)
summary(doe.model1)
@
This is the general model:
begin{equation}
label{eq:doe:model}
y_{ijkl }=mu+ alpha_i + beta_j + gamma_k +( alphabeta)_{ij}
( alphagamma)_{ik }+( betagamma)_{kl }+( alphabetagamma
Seminario EIO UCLM 8/66
9. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
Sweave Example (cont.)
varepsilon_{ijkl},
end{equation}
And here we have a plot of effects:
<<maineff , echo=FALSE , fig=TRUE >>=
plot(c(-1, 1), ylim = range(ss.data.doe1$score),
coef(doe.model1 )[1] + c(-1, 1) * coef(doe
type ="b", pch =16)
abline(h=coef(doe.model1 )[1])
@
%input{section2}
end{document}
Seminario EIO UCLM 9/66
10. Design of Experiments
EL Cano and JM Moguerza and A Rechuk
April 10, 2012
1 Introduction
Design of experiments is the most important took in the Improve phase of the
DMAIC cycle . . . .
> library(SixSigma)
> doe.model1 <- lm(score ~ flour + salt + bakPow +
+ flour * salt + flour * bakPow +
+ salt * bakPow + flour * salt * bakPow,
+ data = ss.data.doe1)
> summary(doe.model1)
Call:
lm(formula = score ~ flour + salt + bakPow + flour * salt + flour *
bakPow + salt * bakPow + flour * salt * bakPow, data = ss.data.doe1)
Residuals:
Min 1Q Median 3Q Max
-0.5900 -0.2888 0.0000 0.2888 0.5900
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 5.5150 0.3434 16.061 2.27e-07 ***
flour+ 1.8350 0.4856 3.779 0.005398 **
salt+ -0.8350 0.4856 -1.719 0.123843
bakPow+ -2.9900 0.4856 -6.157 0.000272 ***
flour+:salt+ 0.1700 0.6868 0.248 0.810725
flour+:bakPow+ 0.8000 0.6868 1.165 0.277620
salt+:bakPow+ 1.1800 0.6868 1.718 0.124081
flour+:salt+:bakPow+ 0.5350 0.9712 0.551 0.596779
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.4856 on 8 degrees of freedom
Multiple R-squared: 0.9565, Adjusted R-squared: 0.9185
F-statistic: 25.15 on 7 and 8 DF, p-value: 7.666e-05
This is the general model:
yijkl = µ + αi + βj + γk + (αβ)ij + (αγ)ik + (βγ)kl + (αβγ)ijk + εijkl, (1)
1
11. And here we have a plot of effects:
q
q
−1.0 −0.5 0.0 0.5 1.0
34567
c(−1, 1)
coef(doe.model1)[1]+c(−1,1)*coef(doe.model1)[2]
2
12. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
Project Example
Strategies
Partial Sweave files can be compiled to get
partial LATEX files. R scripts can Sweave .Rnw
files and“source”.R files. The final document
is obtained by compiling the“master”
LATEX file.
> source("code/myoptions.R")
> source("code/myfunctions.R")
> source("code/mydata.R")
> Sweave("rnw/theorem01.Rnw")
> Sweave("rnw/lesson01.Rnw")
> Sweave("rnw/exercises01.Rnw")
> ...
> texi2pdf("master.tex")Seminario EIO UCLM 12/66
13. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
EADAPU
Seminario EIO UCLM 13/66
14. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
EADAPU - Programa
Sesi´on 1 (4 horas)
1 Introducci´on a la Metodolog´ıa Seis
Sigma.a
2 Herramientas de la fase de definici´on.
3 Herramientas de la fase de medida.
a
Incluye introducci´on a RStudio
Seminario EIO UCLM 14/66
15. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
EADAPU - Programa (cont.)
Sesi´on 2 (4 horas)
1 La importancia de experimentar.
2 Introducci´on al dise˜no de experimentos.
3 Dise˜no de experimentos como
herramienta de mejora.
4 Dise˜no robusto.
5 Dise˜nos avanzados.
Seminario EIO UCLM 15/66
16. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
Contents
1 Statistical Training
Approaches
Examples
Application
2 Six Sigma with R
Six Sigma
R
Packages
Seminario EIO UCLM 16/66
17. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
Publisher
http://www.springer.com/statistics/book/978-1-4614-3651-5
Seminario EIO UCLM 17/66
18. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
Book website
http://www.sixsigmawithr.com/
Seminario EIO UCLM 18/66
19. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
R Package
http://cran.r-project.org/web/packages/SixSigma/index.html
Seminario EIO UCLM 19/66
20. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
Contents
Foreword (Thanks David R´ıos)
Preface
Part I: Basics
Part II: R Tools for the Define Phase
Part III: R Tools for the Measure Phase
Part IV: R Tools for the Analyze Phase
Part V: R Tools for the Improve Phase
Part VI: R Tools for the Control Phase
Part VII: Further and Beyond
Seminario EIO UCLM 20/66
21. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
1. Six Sigma in a Nutshell
Herbert Spencer
“Science is organised knowledge”
Seminario EIO UCLM 21/66
22. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
2. R from the Beginning
Linus Torvalds
“Software is like sex; it’s better when it’s free”
Seminario EIO UCLM 22/66
23. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
3. Process Mapping with R
Charles Franklin Kettering
“A problem well stated is a problem half
solved”
Seminario EIO UCLM 23/66
24. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
A Process Map
Six Sigma Process Map
Paper Helicopter Project
INPUTS
X
operators
tools
raw material
facilities
INSPECTION
INPUTS
sheets
...
Param.(x):width NC
operator C
Measure pattern P
discard P
Featur.(y):ok
ASSEMBLY
INPUTS
sheets
Param.(x):operator C
cut P
fix P
rotor.width C
rotor.length C
paperclip C
tape C
Featur.(y):weight
TEST
INPUTS
helicopter
Param.(x):operator C
throw P
discard P
environment N
Featur.(y):time
LABELING
INPUTS
helicopter
Param.(x):operator C
label P
Featur.(y):label
OUTPUTS
Y
helicopterLEGEND
(C)ontrollable
(Cr)itical
(N)oise
(P)rocedure
Seminario EIO UCLM 24/66
25. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
4. Loss Funtion Analysis with R
W. Edwards Deming
Defects are not free. Somebody makes them,
and gets paid for making them
Seminario EIO UCLM 25/66
26. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
A Loss Function Example
Loss Function Analysis
10 mm. Bolts Project
0e+00
1e−04
2e−04
3e−04
4e−04
5e−04
LSL USL
T
9.6 9.8 10.0 10.2 10.4
Observed Value
CostofPoorQuality
L = 0.002 ⋅ (Y − 10)2
Data
CTQ: diameter
Y0 = 10
∆ = 0.5
L0 = 0.001
Size = 1e+05
Mean = 10.0308
k = 0.002
MSD = 0.0337
Av.Loss = 1e−04
Loss = 6.7441
Seminario EIO UCLM 26/66
27. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
5. Measurement System Analysis
Lord Kelvin
“If you cannot measure it,
you cannot improve it.”
Seminario EIO UCLM 27/66
28. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
MSA with R
Six Sigma Gage R&R Study
Helicopter Project
Components of Variation
Percent
0
20
40
60
80
G.R&R Repeat Reprod Part2Part
%Contribution %Study Var
Var by Part
var
1.0
1.2
1.4
1.6
1.8
prot #1 prot #2 prot #3
q
q
q
q
q
q
q
q
q
qq
q
q
q
q
qq
q
q
q
q
q
qq
q
q
q
Var by appraiser
var
1.0
1.2
1.4
1.6
1.8
op #1 op #2 op #3
q
q
q
q
q
q
q
q
q
qq
q
q
q
q
qq
q
q
q
q
q
qq
q
q
q
Part*appraiser Interaction
var
1.1
1.2
1.3
1.4
1.5
1.6
1.7
prot #1 prot #2 prot #3
q
q
q
q
q
q
q
q
q
op #1
op #2
op #3
x Chart by appraiser
part
var
1.1
1.2
1.3
1.4
1.5
1.6
1.7
prot #1 prot #2 prot #3
q
q
q
op #1
prot #1 prot #2 prot #3
q
q
q
op #2
prot #1 prot #2 prot #3
q
q
q
op #3
R Chart by appraiser
part
var
0.1
0.2
0.3
0.4
0.5
prot #1 prot #2 prot #3
q
q
q
op #1
prot #1 prot #2 prot #3
q
q
q
op #2
prot #1 prot #2 prot #3
q
q
q
op #3
Seminario EIO UCLM 28/66
29. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
6. Pareto Analysis with R
Ovidio
Causa latet: vis est notissima. [The cause is
hidden, but the result is known.]
Seminario EIO UCLM 29/66
30. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
Cause-and-effect diagram
Six Sigma Cause−and−effect Diagram
Paper Helicopter Project
Flight Time
Operator
operator #1
operator #2
operator #3
Environment
height
cleaning
Tools
scissors
tape
Design
rotor.length
rotor.width2
paperclip
Raw.Material
thickness
marks
Measure.Tool
calibrate
model
Seminario EIO UCLM 30/66
31. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
Pareto Chart
Delays
Materials
Customer
Training
Rework
Errors
Rain
Wind
Permissions
Inadequate
Temperature
Pareto Chart for b.vector
Frequency
0204060
q
q
q
q
q
q
q
q
q
q
q
80%
CumulativePercentage
Seminario EIO UCLM 31/66
32. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
7. Process Capability Analysis
Johann Wolfgang von Goethe
One cannot develop taste from what is of
average quality but only from the very best.
Seminario EIO UCLM 32/66
33. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
Capability Analysis Output
Six Sigma Capability Analysis Study
Winery Project
Histogram & Density
LSL
Target
USL
740 745 750 755 760
Check Normality
q
q
q q
qq
qqq
qq
qqqqq
q q
q
q Shapiro−Wilk Test
p−value: 0.07506
Lilliefors (K−S) Test
p−value: 0.2291
Normality accepted when p−value > 0.05
Density Lines Legend
Density ST
Theoretical Dens. ST
Density LT
Theoretical Density LT
Specifications
LSL: 740
Target: 750
USL: 760
ProcessShort Term
Mean: 749.7625
SD: 2.1042
n: 20
Zs: 3.14
Long Term
Mean: 753.7239
SD: 2.6958
n: 40
Zs: 2.33
DPMO: 9952.5
IndicesShort Term
Cp: 1.5841
CI: [1.4,1.7]
Cpk: 1.5465
CI: [1.4,1.7]
Long Term
Pp: 1.2365
CI: [1.1,1.3]
Ppk: 0.7760
CI: [0.7,0.8]
Seminario EIO UCLM 33/66
34. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
8. Charts with R
John Tukey
“The greatest value of a picture is when it
forces us to notice what we never expected to
see.”
Seminario EIO UCLM 34/66
35. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
Multi-vari chart
Multi−vari chart for Volume by color and operator
Filler
Volume
14
15
16
17
18
1 2 3
q
q
q
q
q
q
q
q
q
q
q
q
B
1
q
q
qq
q
q
q
q
q
q
q
q
C
1
q
q
q
q
q
q
q
q
q
q
q q
B
2
14
15
16
17
18
q
q
q
q
q
qq
q
q
q
q
q
C
2
14
15
16
17
18
q q q
q
q qq q
q
q
q
q
B
3
1 2 3
q q q
q
q
q
q q
q
q q q
C
3
batch
1 2 3 4q q q q
Seminario EIO UCLM 35/66
36. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
9. Statistics and Probability with R
Aaron Levenstein
“Statistics are like bikinis. What they reveal is
suggestive, but what they conceal is vital.”
Seminario EIO UCLM 36/66
37. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
Distributions
0 1 2 3 4
0.00.3
Hypergeometric
Elements in class A
Probability
0 10 30
0.000.10
Geometric
Items extracted until first success
Probability
10 20 30 40
0.000.06
Negative Binomial
Number of trials until 3 events
Probability
0 5 10 20
0.000.15
Poison
Number of successful experiments per unit
Probability
0 1 2 3 4 5
0.00.6
Exponential
Random Variable X
ProbabilityDensity
0 2 4 6
0.00.40.8
Lognormal
Random Variable X>0
ProbabilityDensity
−0.5 0.5 1.5
0.00.61.2
Uniform
Random Variable X
ProbabilityDensity
0 2 4 6 8
0.00.20.4
Gamma
Random Variable X
ProbabilityDensity
0.0 0.4 0.8
0.01.02.0
Beta
Random Variable X
ProbabilityDensity
0 2 4 6
0.00.30.6
Weibul
Random Variable X
ProbabilityDensity
−4 0 2 4
0.00.3
t−Student
Random Variable X
ProbabilityDensity
1.73
95%
5%
10 30 50
0.000.06
Chi−squared
Random Variable X
ProbabilityDensity
30.14
95% 5%
0 1 2 3 4
0.00.6
F
Random Variable X
ProbabilityDensity
2.34
95%
5%
Seminario EIO UCLM 37/66
38. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
10. Statistical Inference with R
George E.P. Box
“All models are wrong; some models are
useful.”
Seminario EIO UCLM 38/66
39. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
Confidence Interval Example
Confidence Interval for the Mean
Mean:
StdDev:
n:
Missing:
950.016
0.267
120
0
95% CI:
P−Var:
t:
[949.967, 950.064]
unknown
1.98
Shapiro−Wilks
Normality Test
0.985
p−value: 0.19
q
qq
q
qqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqq
qqq
q
Normal q−q Plot
0.0
0.5
1.0
1.5
949.0 949.5 950.0 950.5
Value of len
density
Histogram & Density Plot
Seminario EIO UCLM 39/66
40. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
11. Design of Experiments with R
R.A. Fisher
“Sometimes the only thing you can
do with a poorly designed
experiment is to try to find out what
it died of”
Seminario EIO UCLM 40/66
41. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
The Importance of Experimenting
“An engineer who does not know
experimental design is not an
engineer”
Comment made by to one
of the authors [of“Statistics
for experimenters”] by an
executive of the Toyota
Motor Company.
Seminario EIO UCLM 41/66
42. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
12.Process Control with R
Walter A. Shewhart
“Special causes of variation may be found and
eliminated.”
Seminario EIO UCLM 42/66
43. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
Control Chart Plotting
p Chart
for stockouts
Group
Groupsummarystatistics
1 3 5 7 9 11 13 15 17 19 21
0.000.050.100.150.200.25
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
q
LCL
UCL
CL
q
Number of groups = 22
Center = 0.1212294
StdDev = 0.3263936
LCL is variable
UCL is variable
Number beyond limits = 1
Number violating runs = 0
Seminario EIO UCLM 43/66
44. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
13. Other Tools and
Methodologies
Johann Wolfgang von Goethe
Instruction does much, but encouragement
everything.
Seminario EIO UCLM 44/66
45. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
Other topics
Failure Mode, Effects, and Criticality
Analysis
Design for Six Sigma
Lean
Gantt Chart
Some Advanced R Topics
Seminario EIO UCLM 45/66
46. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
Case Study
Seminario EIO UCLM 46/66
47. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
Helicopter Template
> ss.heli()
null device
1
> #vignette("HelicopterInstructions") t
Seminario EIO UCLM 47/66
48. Six Sigma with R | Paper Helicopter template
cut
fold ↑ fold ↓
tape?
cut
fold↓↓
cut
fold↑↑
cuttape?
tape?
clip?
min
(6.5cm)
std
(8cm)
max
(9.5cm)
←bodylength→
← body width →min
(4cm)
min
(4cm)
max
(6cm)
max
(6cm)
min
(6.5cm)
std
(8cm)
max
(9.5cm)
←wingslength→
49. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
Enjoy the Case Study!
Seminario EIO UCLM 49/66
50. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
Enjoy the Case Study!
Seminario EIO UCLM 49/66
51. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
Book Production
Reproducible Research
Written applying reproducible research
techniques. All figures (except screen
captures) are generated while compiling the
book using R code.
Seminario EIO UCLM 50/66
52. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
The DMAIC Cycle
Seminario EIO UCLM 51/66
53. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
Six Sigma Roles
In Six Sigma, everyone in the organization has
a role in the project. Six Sigma methodology
uses an intuitive categorization of these roles.
Seminario EIO UCLM 52/66
54. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
Six Sigma Roles
In Six Sigma, everyone in the organization has
a role in the project. Six Sigma methodology
uses an intuitive categorization of these roles.
Seminario EIO UCLM 52/66
55. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
Why 6 and why Sigma
Sigma refers to the Z-Score of the process:
Z = min
(USL − x)
σ
,
(x − LSL)
σ
; ZLT = ZST −1,5.
CTQ
Frequency
Short Term
Long Term
1.5σ 4.5σ
> (1-pnorm(4.5))*(10^6)
[1] 3.397673
DPMO
Seminario EIO UCLM 53/66
56. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
So what?
Seminario EIO UCLM 54/66
57. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
So what?
The Scientific Method
Seminario EIO UCLM 54/66
58. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
The Scientific Method and Six
Sigma
Define
Ask a question
Measure
Analyze
Improve
Control
Do some background
research
Construct a hypothesis
Test the hypothesis
with an experiment
Analyze the data and
draw conclusions
Communicate results
DMAIC Cycle Scientific Method
Seminario EIO UCLM 55/66
59. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
The Key to Success
“Six Sigma speaks the language of business”
ISO 13053-1:2011
Six Sigma methodology is a quality paradigm
that translates the involved scientific
methodology into a simple way to apply the
scientific method within every organization.
Seminario EIO UCLM 56/66
60. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
The R Project
http://www.r-project.org
Seminario EIO UCLM 57/66
61. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
The R Environment
Seminario EIO UCLM 58/66
62. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
Reproducible Research
knitr, pgfSweave: enhanced options for
Sweave
exams: Automatic generation of printable
exams
odfWeave: Open Document format
documents generation
More in the“Reproducible Research”Task
View at CRAN.
http://cran.r-project.org/web/views/
ReproducibleResearch.html
Seminario EIO UCLM 59/66
63. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
Package RGIFT
Open format GIFT
Integration with Moodle
Automatic correction
http://cran.r-project.org/web/
packages/RGIFT/
Seminario EIO UCLM 60/66
64. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
Community
Community
4131 packages at CRAN (18/11/2012)a
Bioconductor, R-forge, Github,
Omegahat.
Task views
Manuals
Publications
http:
//cran.r-project.org/web/packages/
a
4181 04/12
Seminario EIO UCLM 61/66
65. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
R Interfaces
GUI, IDE
RStudio
Eclipse + StatET
EMACS + EES
Deducer
. . .
Seminario EIO UCLM 62/66
66. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
R Interfaces (cont.)
Seminario EIO UCLM 63/66
67. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
http://r-es.org/
Seminario EIO UCLM 64/66
68. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
http://www.r-project.org/useR-2013
Seminario EIO UCLM 65/66
69. Seis Sigma con R
December, 2012
Emilio L. Cano
Statistical Training
Approaches
Examples
Application
Six Sigma with R
Six Sigma
R
Packages
Discussion
Thanks !
emilio.lopez@urjc.es
@emilopezcano
http://www.sixsigmawithr.com
Seminario EIO UCLM 66/66