These slides were presented at the Use R! 2011 Conference, held in the University of Warwick (Coventry) in August 2011. It was one of the presentations of the Lightning Talks session.

1. Six Sigma is Possible with R
And Even Better
Emilio Lopez
Department of Statistics and Operations Research
Rey Juan Carlos University (Madrid)
University of Warwick, August 2011
The R User Conference 2011 - Lightning Talk 1/15

2. The DMAIC Cycle
The R User Conference 2011 - Lightning Talk 2/15

3. The Scientific Method
http://electroncafe.wordpress.com/2011/
05/04/scientific-process-rage/
The R User Conference 2011 - Lightning Talk 3/15

4. The Scientific Method & Six Sigma
DMAIC Cycle Scientific Method
Ask a question
Define
Do some background
Measure research
Construct a hypothesis
Analyze
Test the hypothesis
with an experiment
Improve
Analyze the data and
draw conclusions
Control
Communicate results
The R User Conference 2011 - Lightning Talk 4/15

5. The key to success
Science is organized knowledge.
Herbert Spencer
Six Sigma is a quality paradigm which translates the
complicated scientific terminology into a simple way
to apply the scientific method within every
organization.
The R User Conference 2011 - Lightning Talk 5/15

6. Six Sigma Software
The R User Conference 2011 - Lightning Talk 6/15

7. Six Sigma Software
The R User Conference 2011 - Lightning Talk 7/15

8. R Challenges
Why Not
Six Sigma uses Statistics.
Six Sigma is based in the Scientific Method.
Six Sigma should use R!.
Outstanding advantages
Every Statistical Tool even in base installation
Extending possibilities
Powerful graphics
The R User Conference 2011 - Lightning Talk 8/15

9. Packages
qcc Shewhart quality control charts for
continuous, attribute and count data
IQCC Builds statistical control charts with
exact limits for univariate and
multivariate cases.
qualityTools This is a package for teaching
statistical methods in the field of Quality
Science [. . . ] The focus is on teaching
[. . . ]
SixSigma Our effort for spreading the R thinking
along Six Sigma practitioners.
The R User Conference 2011 - Lightning Talk 9/15

10. Six Sigma with R - Springer Use R! Series
Features
Title:
Six Sigma with R
Due 2012
350 pages approx.
Wide background
scope
Examples, a Case
Study and practices
The R User Conference 2011 - Lightning Talk 10/15

11. Process Map
Six Sigma Process Map
operators
INPUTS
tools
X raw material
facilities
INSPECTION ASSEMBLY TEST LABELING
sheets sheets helicopter helicopter
...
INPUTS
INPUTS
INPUTS
INPUTS
Param.(x): width NC Param.(x): operator C Param.(x): operator C Param.(x): operator C
operator C cut P throw P label P
Measure pattern P fix P discard P Featur.(y): label
discard P rotor.width C environment N
Featur.(y): ok rotor.length C Featur.(y): time
paperclip C
tape C
Featur.(y): weight
LEGEND
helicopter
(C)ontrollable OUTPUTS
(Cr)itical
(N)oise
Y
(P)rocedure
Paper Helicopter Project
The R User Conference 2011 - Lightning Talk 11/15

12. Gage R&R
Six Sigma Gage R&R Study
Components of Variation Var by Part
1.8
q
80 q
q
q
q
1.6
60
q
q
Percent
1.4
var
40 q
q
q
q q
q
1.2
20 q
q
q
q q
1.0 q
0
q
G.R&R Repeat Reprod Part2Part
prot #1 prot #2 prot #3
%Contribution %Study Var
R Chart by appraiser Var by appraiser
prot #1 prot #2 prot #3
1.8
q q
op #1 op #2 op #3 q
0.5 q
q q
q q
1.6
0.4 q
q q
q 1.4
var
0.3 q
var
q
q q q
q q q
q
0.2 1.2
q q q q
q
q q q
0.1
q q 1.0 q
q
prot #1 prot #2 prot #3 prot #1 prot #2 prot #3
op #1 op #2 op #3
part
x Chart by appraiser Part*appraiser Interaction
prot #1 prot #2 prot #3
1.7 q
op #1 op #2 op #3
1.7 q
1.6 q
1.6 q q 1.5
var
1.5 1.4
var
1.4 q
1.3
q q
1.3
q 1.2
1.2 q
q q
1.1 q q 1.1 q
q
prot #1 prot #2 prot #3
prot #1 prot #2 prot #3 prot #1 prot #2 prot #3
op #1 op #3
part op #2
Helicopter Project
The R User Conference 2011 - Lightning Talk 12/15

13. Capability Analysis
Six Sigma Capability Analysis Study
Histogram & Density Density Lines Legend
Target Density ST
Theoretical Dens. ST
Density LT
Theoretical Density LT
LSL USL Specifications
LSL: 740
Target: 750
USL: 760
Short Term Process Long Term
740 745 750 755 760
Mean: 749.7625 Mean: 752.8443
Check Normality SD: 2.1042 SD: 2.9577
n: 20 n: 40
Shapiro−Wilk Test Zs: 3.14 Zs: 2.42
q
p−value: 0.07506 DPMO:
q
Short Term Indices Long Term
qq
q qq
Lilliefors (K−S) Test Cp: 1.5841 Pp: 1.1270
qq
qq
qq
q p−value: 0.2291 CI: [1.1,2.1] CI: [0.9,1.4]
qq
qq
q
q Cpk: 1.5465 Ppk: 0.8065
CI: [1.1,2.1] CI: [0.9,1.4]
Normality accepted when p−value > 0.05
Winery Project
The R User Conference 2011 - Lightning Talk 13/15

14. Open Platform for Quality Methodologies
Open Platform for Quality Methodologies
Improving the European Factory
FP7 PPP Funding Scheme
Looking for Partners
Other Projects
We are available for other projects that need
partners in this area
The R User Conference 2011 - Lightning Talk 14/15

15. Conclusion
Thanks
We hope we will be able to convince Six Sigma
practitioners that not only is it possible with R, but
it is BETTER with R.
@emilopezcano | emilio.lopez@urjc.es
The R User Conference 2011 - Lightning Talk 15/15