Professional Documents
Culture Documents
Executive The success of a Six Sigma programme in an organization depends to a large extent on the
success of the Six Sigma projects, which in turn depends on how the team handles the prob-
Summary lem and whether the right combination of tools is being applied to address the root cause. The
Six Sigma toolbox consists of a wide range of tools comprising, on the one hand, simple and
commonly used tools like flow charts, Pareto analysis, and cause-and-effect diagram and the
more advanced statistical tools like design of experiments, regression analysis and many more,
on the other hand. While the simple tools are easy to apply, understand, and analyse, engi-
neers perceive the more advanced tools difficult to comprehend. Design of experiments (DOE)
is one such tool. Two well-known approaches of design of experiments are the Classical DOE,
pioneered by Sir Ronald A Fisher and the Taguchi approach, pioneered by Dr Genichii Taguchi.
A third approach to experimental design—the Shainin DOE techniques, offered by Dr Dorian
Shainin–can be considered as a very good alternative to the other approaches. They are much
simpler than the factorial designs, response surface designs, and orthogonal arrays of the
conventional approaches of DOE, but at the same time are recognized as being very powerful
and effective in solving the chronic quality problems that plague most manufacturers. Shainin
DOE basically works at eliminating suspected process variables by mostly using seven differ-
ent tools, viz.,
• Multi-Vari Charts
• Component Search
• Paired Comparison
• Variable Search
• Full Factorials
• B vs. C (Better vs. Current) Analysis
• Scatter Plots or Realistic Tolerance Parallelogram Plots.
Though not very well documented, these tools have proved to be the key drivers in the suc-
cess of many companies, e.g., Motorola.
This article examines two projects of a leading automotive and general lighting lamp manu-
KEY WORDS facturing company, in which a combination of the standard Six Sigma tools and Shainin tools
has been successfully used to address the root cause of the problems. The advantage of using
Shainin tools is that:
Six Sigma Tools
• Very small sample sizes are required to analyse the problem. Often samples as small as 2
Factorial Designs or 3 are enough to make statistically valid conclusions.
Shainin DOE • Statistical software is not required to analyse the data. In fact, Shainin DOE does not even
require knowledge of complex statistical tools.
Suspected Sources of • It involves employees at all levels, including workers and junior staff in problem solving
Variation that was hitherto a domain of senior technical experts.
• Also, the success of the projects had a very positive effect on the morale of the employees
Red X in terms of convincing them that Six Sigma is not all about using complex statistical tools.
14 SIMPLIFYING THE SIX SIGMA TOOLBOX THROUGH APPLICATION OF SHAININ DOE TECHNIQUES
designed experiments, changes are deliberately intro- source through a process of elimination (Shainin, 1993b),
duced into the process to better understand which of called progressive search. These techniques, also referred
the Xs are affecting the output variable. There are two to as the Shainin System for quality improvement, de-
well-known approaches to experimental design. The first veloped over a period of over 40 years, are simple but at
approach is the classical design of experiments credited the same time powerful and easier to interpret and im-
to Sir Ronald Fisher who initially experimented in the plement in an industrial environment. In a way, these
field of agriculture. However, this method is now widely may be considered as the non-parametric equivalent of
used in many fields. The second approach is the Taguchi Taguchi’s DOE as they do not make any restrictive as-
approach pioneered by Dr Genichi Taguchi of Japan who sumptions about population parameters.
adopted the classical approach to reintroduce the con-
cept of orthogonal arrays. The commonly used classical “Ninety per cent of the tolerances and specifications are
Design of Experiment (DOE) tools are the family of fac- arbitrarily decided and are not correct for the intended
torial experiments consisting of full factorial designs and applications” (http://www.ind.tuv.com). This of course
in no small measure contributes to a host of what are
fractional factorial designs. A full factorial allows us to
called ‘chronic quality problems’ – problems that keep
test all possible combinations of factors affecting output
recurring. Finding solutions to these problems then be-
in order to identify which ones are more dominant. A
fractional factorial tests just a fraction of the possible comes a major challenge for engineers and quality prac-
combinations. Though a very popular tool, many engi- titioners. The Shainin techniques are primarily known
neers and quality practitioners find design of experi- to produce breakthrough improvements in eliminating
ments difficult primarily because of the complexity of chronic quality problems. These are highly effective in
having to create the conditions for conducting the ex- pinpointing towards the root cause and validating it.
periments in an industrial environment where interrupt- Applications of the Classical and Taguchi methods in
ing production lines and changing machine settings may various fields have been extensively researched. A few
be sometimes difficult and unproductive. very recent contributions in this area are from Wang and
Ren (2007), Singh, Maheswari and Pandey (2007), See
SHAININ DOE APPROACH and Wong (2008), Abdo (2008), Rao, et al (2008), and
An alternative to the Classical and Taguchi experimen- Anawa, et al (2008). In contrast, the Shainin system has
tal design is the lesser known but much simpler Shainin not been extensively reviewed, academically, and very
DOE approach developed and perfected by Dorian limited studies have been carried out in this area. Bhote
Shainin (Bhote and Bhote, 2000), consultant and advisor (1990) compared Shainin techniques with Design of Ex-
to over 750 companies in America and Europe. Shainin’s periments and Taguchi methods, in the context of the
philosophy has been, “Don’t let the engineers do the electronics industry and concluded that the Shainin tech-
guessing; let the parts do the talking.” Shainin recog- niques are simpler, less costly, and statistically more
nized the value of empirical data in solving real-world powerful than the other two. Logothetis (1990) also
problems. He introduced the concept of Red X, the domi- evaluated the Shainin techniques in relation to the
nant source of variation, among the many sources of Taguchi methods and statistical process control meth-
variation of a problem that inevitably accounts for nearly ods. Bhote (1991) and Bhote and Bhote (2000) described
all the unwanted effect. In fact, Shainin (Shainin, 1995; these tools in their books, but there have been many criti-
1993b), classified all causes of chronic quality problems cisms regarding their claims and the tools described.
into three X’s, viz., the Red X, the Pink X- the second Though Nelson (1991), Moore (1993), and more recently,
most important cause(s), and the Pale Pink X – the third Zeigel (2001) criticized the Shainin System as unsubstan-
most important cause(s). According to him, these three tiated and exaggerated, Steiner, et al (2008), are of the
Xs together account for over 80 per cent of the variation opinion that some of the ideas behind the Shainin Sys-
that is allowed within the specification limit and when tem are genuinely useful. Goodman and Wyld (2001)
captured, reduced, and controlled, these can eliminate offered a case study involving the use of Shainin DOE
this variation. Shainin developed techniques (Shainin in an industrial operation. This study suggested that ‘the
and Shainin, 1990; 1992a; 1992b; 1993a; 1993b; Shainin, Shainin methodology is very practical and can be easily
Shainin and Nelson, 1997) to track down the dominant executed in many settings, making it one of the most
16 SIMPLIFYING THE SIX SIGMA TOOLBOX THROUGH APPLICATION OF SHAININ DOE TECHNIQUES
Shainin DOE Tools: An Overview of Select Tools And, in the last case of high cyclical variation, the team
Shainin DOE basically works at eliminating suspected needs to focus on identifying which stream causes the
process variables (Xs) mostly by using seven different highest variation to get down to the root cause. DeMast,
tools (Bhote, 1991): Roes and Does (2001) have studied this technique in
detail.
• Multi-Vari Analysis
Component search: Component search technique is a
• Component Search
simple but powerful tool to lower down the number of
• Paired Comparison
suspected sources of variation to the family of Red X or
• Variable Search
the Red X itself. This technique can be used primarily in
• Full Factorials
assembly operations, i.e., when a product can be disas-
• B vs. C (Better vs. Current) Analysis
sembled and re-assembled, as it allows finding the com-
• Scatter Plots or Realistic Tolerance Parallelogram
ponent of an assembly that is most likely to cause the
Plots
problem. This technique is used to find the suspected
Subsequently, Bhote and Bhote (2000) added three more source of variation (SSV) that either originates from the
tools to the list, viz., Product/Process Search, Concen- assembly process or the components in the assembly.
tration chart, and Response Surface Methodology. How- Thus, the various stages of the component search method
ever, our aim is to study the application of a few basic (Bhote, 1991) are:
but effective tools along with their application in Six
• Ballpark stage: This stage determines whether Red X
Sigma projects.
or Pink X is actually present among the components
A brief discussion and understanding is necessary be- or factors being investigated.
fore these tools are applied: • Elimination: The second step involves elimination of
all unimportant main effects and their associated in-
Multi-vari analysis: Multi-vari analysis is used to re- teraction effects.
duce a large number of suspected sources of variation • Capping run: This stage consists of re-verification of
to a smaller family of variables containing the dominant the important and unimportant effects.
source of variation. A multi-vari analysis is based on • Factorial analysis: Once the important and unimpor-
the assumption that any process variation can occur as tant factors have been double-checked, factorial
a result of three factors, viz., analysis is used to determine the magnitude of the
important SSVs and their interactions.
• Positional or Part-to-Part Variation
• Temporal or Time-to-Time Variation Once the problem components are identified, a paired
• Cyclical or Stream-to-Stream Variation comparison can be used to further identify the para-
meters in the component causing the problem.
Each type of variation is individually measured using a
run of approximately 3 to 5 units produced consecutively Paired comparison: Paired comparison is similar to com-
at any given time. After a time lapse, another run of 3 to ponent search except that it is used when components
5 units are produced. This process is repeated until 80 cannot be reassembled or disassembled. This technique
per cent of the out-of-control variation in the process is uses a small sample consisting of good parts and bad
captured. A plot of these results indicates which one of parts to further narrow down the range of potential
the three variations is maximum. Simple tools like the sources of variation. The good and bad parts are selected
average and the range are then used to identify which on the basis of a suitable parameter related to the prob-
type of variation out of these three is the highest. In case lem. Selecting the good parts implies selecting the Best
the positional or part-to-part variation is the highest, the of Best (BOB) parts and selecting the bad parts implies
source of variation is usually attributed to the machine selecting the Worst of Worst (WOW) parts with respect
or the process design. Further tools can be used to iden- to the desired response. The terms BOB and WOW are
tify the exact cause. If time to time variation is high, the attributed to Shainin et al (1997). Steiner et al (2008) are
team needs to try and identify the event that has caused of the opinion that this comparison of extreme values of
the shift in average in a variable over a period of time. the response variable is unique to the Shainin System
18 SIMPLIFYING THE SIX SIGMA TOOLBOX THROUGH APPLICATION OF SHAININ DOE TECHNIQUES
Table 3: The Shainin DOE tools
Some other benefits reported by users of Shainin DOE LAMP MANUFACTURING COMPANY
techniques are accrued by virtue of their direct role in:
Company Profile
• solving chronic quality problems
The company is a leading manufacturer of automotive
• reducing process variations
and general lighting lamps with a group turnover ex-
• eliminating defects
ceeding Rs 250 crore. With exports to nearly 60 different
• reducing/eliminating scrap/rework/testing
countries, it is the largest exporter of lamps in the coun-
• reducing cost of poor quality
try. The company gets nearly 33 per cent of its income
• increasing field reliability of products
from exports and the rest from the domestic segment. It
• improving financial parameters, like return on invest-
has five fully integrated state-of-the-art manufacturing
ment (ROI) and market share, etc.
facilities at Noida in NCR and Dehradun and Haridwar
Among the Shainin tools, factorial designs and scatter in Uttaranchal. The five units together deliver over 150
plots are commonly known and used. However, the million lamps annually, all benchmarked to international
main differentiators of the Shainin tools are component regulations for quality, performance, and safety. One of
search method, paired comparison method, product/ the five facilities, is a 100 per cent export-oriented unit
process search, and B vs. C analysis. In order to high- (EOU), catering to exports mostly to USA and European
light the application of these tools, we choose two countries like Italy and Germany. The company also has
projects from the selected predominantly automotive all major quality certifications like ISO 9001:2000, ISO/
lamp manufacturing company known to apply Shainin TS 16949:2002, ISO 14000:2004, and OHSAS 18001:2007.
tools extensively in their Six Sigma projects. It saw a change in ownership in the year 2007 following
20 SIMPLIFYING THE SIX SIGMA TOOLBOX THROUGH APPLICATION OF SHAININ DOE TECHNIQUES
The Six Sigma Projects Selected Figure 1: A Model of the Halogen Lamp in Project A
Count
60
some of the technical considerations of the projects are 0.2 40
beyond the scope of this paper; our attempt has been to 0.1 20
focus on the application of the Shainin tools.
0.0 0
The first project, Project A, was a green belt project. A Defect Sub Main Mount Shell Others
Filament Filament Tilt Crack
team leader, a sponsor, and three team members were a Bend Bend
part of this project. The project concerning defects in a Count 0.19 0.12 0.10 0.05 0.02
halogen lamp was a priority project as the price of non- Percent 39.6 25.0 20.8 10.4 4.2
Cum % 39.6 64.6 85.4 95.8 100.0
conformance in this case was very high. A DMAIC meth-
odology was followed in the project and it was
Gage R & R Study
completed within two months. This project demonstrated
To evaluate the effectiveness of the measurement sys-
the application of the Shainin techniques, product/proc-
tem, a Gage Repeatability and Reproducibility (Gage R
ess analysis, and multi-vari analysis along with a few
& R) study was conducted with the help of MINITAB.
other basic Six Sigma tools to bring down the defect rate.
Repeatability measures the variability in measurements
Project A with one measurement instrument and one operator
while measuring identical characteristics on the same
The problem in this case was that of defects in the fila- part. Reproducibility measures the variability in meas-
ment of a halogen lamp (Figure 1). This particular lamp urements with one measurement instrument by differ-
consisted of two coiled tungsten filaments, viz., a sub- ent operators, again while measuring identical characte-
filament and a main-filament mounted in a glass enve- ristics on the same part. Repeatability captures the in-
lope and filled with a small amount of halogen gas. At strument variability and reproducibility captures the
the outset, a Pareto analysis (Figure 2) indicated that operator-to-operator variability. The total Gage R & R
maximum variation was coming from a bend in the sub- in this case was not significant since it was less than 20
filament of the lamp. As a result of this problem, the per cent. So measurement system variability was elimi-
wastage was estimated to be 0.19 per cent. A project nated.
charter was prepared, the problem was defined as ‘sub-
filament bend,’ and a target was established to reduce In this phase, potential factors causing the bend were
the sub-filament bend wastage to 0.05 per cent. brainstormed. A brief description of the sleeving pro-
WORKER
METHOD
22 SIMPLIFYING THE SIX SIGMA TOOLBOX THROUGH APPLICATION OF SHAININ DOE TECHNIQUES
sample selection can be done by deciding on the lot size and for the shield tilt is 11. Further, if the endcount is
to be produced and then selecting 8 BOB and 8 WOW ≥ 6, then the parameter is considered significant at 90
parts from this lot based on the response variable. per cent level of significance and if total count ≥ 7, it is
considered significant at 95 per cent level of significance.
In this case, the second method was used. A lot size of
In this case, endcount for all three parameters were sig-
100 pieces was manufactured and 16 units – 8 BOB and
nificant. So, the team identified and studied the specifi-
8 WOW – were selected based on the response variable,
cations for the good range for all three SSVs. An analysis
i.e., the leg angle in this case. The BOB pieces were de- and comparison of these values with the design specifi-
cided from among the ones with minimum to no bends cation indicated that the leg angle of the sleeving ma-
in the sub-filament and the WOW pieces were chosen chine required certain modifications. As a counter
from among the ones with considerable amount of bend measure to improve the leg angle, the sleeving machine
in the leg angle, thus providing a comparison of extreme heads were suitably modified. Samples taken from the
values of the response. All the three SSVs were meas- process after this modification indicated that the wast-
ured. The observations for each of the SSVs arranged in
age from sub-filament bend had come down signifi-
ascending order are shown in Table 4.
cantly, but not to the target figure of 0.05 per cent as
The observations were analysed by using the endcount desired.
technique, given by Bhote and Bhote (2000) (see Tukey,
Shainin DOE Mult-Vari Analysis
1959 for more on endcount). This technique is briefly
described now. First of all, the top count is the number Once the angle was taken care of, the team now moved
of BOBs before changeover to WOWs. The bottom count on to investigate the third SSV, i.e., the shield tilt. It took
is the number of WOWs from the bottom until the first up a Shainin DOE multi-vari analysis, which has been
changeover to BOB. The endcount is defined as the sum described in the tools overview section. All three varia-
of the top count and the bottom count. As an example, tions, viz., part–to-part, head–to-head, and time-to-time
in Table 4, if we consider the response for leg angle with variations were studied for the third SSV, i.e., the shield
sleeves, the number of Bs from the top before changeover tilt. The part-to-part variation based on the range was
to G is 6. This is the top count. And the number of Gs 2.23. The head-to-head variation and the time-to-time
from the bottom before changeover to B is also 6. This is variation came out as 0.79 and 0.530333 respectively.
the bottom count. And, therefore, the total count is 12. Thus, the highest variability was coming from the part-
Similarly, the count for the leg angle with sleeve is 10 to-part variation.
LSL LSL
Process Data
Cp 1.70
CPU -0.06
CPL 3.45
Cpk -0.06
2.5 2.6 2.7 2.8 2.9
Overall Capability
Observed Performance Exp. “Within” Performance Exp. “Overall” Performance
Pp 1.56
PPU -0.05 PPM < LSL 0.00 PPM < LSL 0.00 PPM < LSL 0.00
PPL 3.17 PPM > USL 53333.33 PPM > USL 566216.02 PPM > USL 560797.47
Ppk -0.05 PPM Total 53333.33 PPM Total 566216.02 PPM Total 560797.47
24 SIMPLIFYING THE SIX SIGMA TOOLBOX THROUGH APPLICATION OF SHAININ DOE TECHNIQUES
brainstorming, the suspected sources of variation were given by Shainin (1993b) and Bhote and Bhote (2000).
identified as: Here is a brief description of an application of this
method. In this method, 10 units — 5 BOB and 5 WOW
i. Resistance of the wire — were first identified from the existing process based
ii. Pitch variation
on the response variable. All SSVs were then measured
Further, the resistance of the coil wire depends on four for each part. The response variable, i.e., current, in this
parameters, viz., case, was also measured.
26 SIMPLIFYING THE SIX SIGMA TOOLBOX THROUGH APPLICATION OF SHAININ DOE TECHNIQUES
the improvement phase. This is usually achieved by Table 8: Modifications in Coil Diameter Specifications
documentation and standardization of the control meas- in Project B
ures. To ensure that the solution worked, the following Coil Diameter Specifications
steps were undertaken. Before After
Main-Filament (1.00 ± 0.2) mm (1.03 ± 0.2) mm
Table 6: B vs. C Analysis in Project B
Sub-Filament (0.96 ± 0.2) mm (0.99 ± 0.2) mm
Main-Filament Data Sub-Filament Data
Sl.No. Response Units Sl.No. Response Units CONCLUSIONS
1 2.71 B 1 2.68 B The key phase of the DMAIC methodology is the meas-
2 2.72 B 2 2.69 B ure and analysis phase. The tools and techniques used
3 2.73 B 3 2.71 B in this phase determine the success or failure of the
4 2.79 C 4 2.78 C
project to a large extent. In both the projects, the Shainin
DOE tools have been very effectively used to pinpoint
5 2.8 C 5 2.79 C
the root causes and validate the improvement actions.
6 2.81 C 6 2.8 C
A classical DOE approach would have meant applica-
(The figures refer to values of current in Ampere.) tion of factorial designs requiring much more time and
effort, and above all, it would have required changes in
Modifications were made in the drawings of the main-
machine settings. Classical DOE requires large data col-
and sub-filament. The coil diameter specifications were
lection to conduct the analysis. In Shainin DOE, small
changed as shown in Table 8. Control charts were used
samples of 5 BOB and 5 WOW pieces were sufficient to
to display the main and sub-filament current to ensure
analyse the data as seen in both the projects. A very im-
continuous monitoring of the process. As per the latest
portant factor is that data collection was done for both
information available from the company in January 2009,
the projects online without disturbing the regular pro-
the current process capability values of this process for
duction. Also, what is more important is not always the
the main filament are: Cp = 4.09, Cpk = 1.96, amounting
exact Six Sigma results but the methodology followed
to remarkably low defects level of just 0.0025 PPM and
to achieve practically zero defects.
for the sub filament: Cp = 3.10 and Cpk = 1.67, amounting
to defects level of only 0.285 PPM indicating that both No statistical software was needed to be used to ana-
processes have capability well over Six Sigma. lyse the data. In fact, Shainin DOE does not even require
knowledge of difficult statistical tools. Simple operation
Table 7: Sub-Filament Observations in Project B like counts, additions, subtractions, etc., make calcula-
tions relatively easy. The projects were completed within
S. Coil No.of Coil MG Response
No. DIA Turns Length (Current) a span of two months. For the company, the estimated
savings from these two projects was more than Rs 2 lakh
1 0.96 22 4.51 48.4 2.75 BOB
per annum. In addition, the success of the projects had a
2 0.962 22 4.44 48.4 2.69 BOB
very positive effect on the morale of the employees in
3 0.962 22 4.56 48.4 2.74 BOB terms of convincing them that Six Sigma works without
4 0.959 22 4.62 48.4 2.66 BOB complex statistics and big jargons.
5 0.956 22 4.45 48.4 2.75 BOB
The subject of the Shainin methods is very vast and this
6 0.95 22 4.61 48.4 2.81 WOW paper highlights the applicability of only a few of the
7 0.951 22 4.51 48.4 2.84 WOW Shainin tools. However, there is a lot of scope for more
8 0.949 22 4.62 48.4 2.83 WOW research on this methodology particularly comparative
9 0.952 22 4.51 48.4 2.84 WOW research of some of the Shainin methods like Paired
Comparison and B vs C Analysis vis-a-vis the more popu-
10 0.951 22 4.51 48.4 2.82 WOW
lar statistical tools like factorial designs and non-para-
metric testing. Although these methods are not
necessarily the best, according to Steiner et al (2006), the
REFERENCES
Abdo, J (2008). “Design of Experiments Technique for Char- Research News, 4(8/9), 1-17.
acterization of Friction in Dry Contact,” International Jour- Harry, Mikel and Schroeder, Richard (2000). Six Sigma: The
nal of Surface Science and Engineering, 2(1/2), 120-138. Breakthrough Management Strategy Revolutionizing the
Adams, Cary W; Gupta, Praveen and Wilson Jr, Charles E World’s Top Corporations, New York: Currency.
(2003). Six Sigma Deployment, Butterworth: Heinemann. Ledolter, J and Swersey, A (1997). “Dorian Shainin’s Variable
Anawa, E M; Olabi, A G and Hashmi, M S J (2008). “Applica- Search Procedure: A Critical Assessment,” Journal of Qual-
tion of Taguchi Method to Optimize Dissimilar Laser ity Technology, 29, 237-247.
Welded Components,” International Journal of Manufac- Logothetis, N (1990). “A Perspective on Shainin’s Approach
turing Technology and Management, 15(2), 219-227. to Experimental Design for Quality Improvement,” Qual-
Anthony, J (1999). “Spotting the Key Variables Using Shainin’s ity and Reliability Engineering International, 6(3), 195-202.
Variable Search Design,” Logistics Information Manage- Moore, D (1993). Review of World Class Quality, by K Bhote,
ment, 12(4), 325-331. 1991. Journal of Quality Technology, Volume 21, 76-79.
Anthony, J and Cheng, A H Y (2003). “Training for Shainin’s Nelson, L S (1991). Review of World Class Quality, by K Bhote,
Approach to Experimental Design Using a Catapult,” 1991. Journal of Quality Technology, Volume 25, 152-153.
Journal of European Industrial Training, 7(8), 405-412.
Pyzdek, Thomas (2001). The Six Sigma Handbook, USA:
Bhote, Keki R (1988). World Class Quality: Design of Experiments McGraw-Hill/Quality Publishing Tucson.
Made Easier, More Cost Effective than SPC, New York:
American Management Association. Rao, R S; Kumar, C G; Prakasham, R S and Hobbs, P J (2008).
‘The Taguchi Methodology as a Statistical Tool for Bio-
Bhote, Keki R (1990). “A More Cost-Effective Approach to DOE technological Applications: A Critical Appraisal,” Biotech-
than Taguchi,” Annual Quality Congress, San Francisco , nology Journal, 3(4), 510-523..
44, 857-862.
See, P C and Wong, K Y (2008). “Using Statistical Design of
Bhote, Keki R (1991). World Class Quality: Using Design of Ex- Experiments to Decide the Effective Parameter Values for
periments to Make it Happen, New York: American Man- a New Hybrid ant Colony Algorithm,” International Jour-
agement Association. nal of Applied Decision Sciences, 1(3), 282-304.
Bhote, K R and Bhote, A K (2000). World Class Quality, 2nd Shainin, D and Shainin, P D (1990). “Analysis of Experiments,”
Edition, New York: American Management Association. 45th Annual Quality Congress Proceedings, ASQC, 1071-
Bregfoyle, Forrest W III; Cupello, James M and Meadows, Beki 1077.
(2001). Managing Six Sigma. New York: John Wiley and Shainin, P D (1992a). “Managing SPC, A Critical Quality Sys-
Sons.. tem Element,” 46th Annual Quality Congress Proceed-
De Mast, J; Schippers, W A J; Does, R J M M and Van den, ings, ASQC, 251-257.
Heuvel E (2000). “Steps and Strategies in Process Im- Shainin, R D (1992b). “Technical Problem Solving Strategies,
provement,” Quality and Reliability Engineering Interna- A Case Study,” 46th Annual Quality Congress Proceed-
tional, 16, 301-311. ings, ASQC, 876-882.
De Mast, J; Roes, K C B and Does, R J M M (2001). “The Multi- Shainin, P D (1993a). “Managing Quality Improvement,” 47th
Vari Chart: A Systematic Approach,” Quality Engineer- Annual Quality Congress Proceedings, ASQC, 554-560.
ing, 13, 437-448.
Shainin, R D (1993b). “Strategies for Technical Problem Solv-
Does, R J M M; Roes, K C B and Trip, A (1999). Statistical Pro- ing,” Quality Engineering, 5, 433-438.
cess Control in Industry, Dordrecht, The Netherlands:
Kluwer Academic Publishers. Shainin, R D (1995). “A Common Sense Approach to Quality
Management,” 49th Annual Quality Congress Proceed-
Eckes, George (2001). The Six Sigma Revolution, New York: John ings, ASQC, 1163-1169.
Wiley & Sons.
Shainin, P D; Shainin, R D and Nelson, M T (1997). “Manag-
Evans, James R and Lindsay, William M (2004). The Manage- ing Statistical Engineering,” 51st Annual Quality Con-
ment and Control of Quality, Singapore: Thompson South gress Proceedings, ASQC, 818-832.
Western.
Singh, S; Maheswari, S and Pandey, P C (2007). “Optimiza-
Goodman, J and Wyld, David C (2001). “The Hunt for Red X: tion of Multiperformance Characteristics in Electric Dis-
A Case Study in the Use of Shainin Design of Experiments charge Machining of Aluminium Matrix Composites
(DOE) in an Industrial Honing Operation,” Management (AMCs) using Taguchi DOE Methodology,” International
28 SIMPLIFYING THE SIX SIGMA TOOLBOX THROUGH APPLICATION OF SHAININ DOE TECHNIQUES
Journal of Manufacturing Research, 2(2), 138-161. Traver, R W (1995). Manufacturing Solutions for Consistent Qual-
Steiner, S H and MacKay, R J (1997-1998). “Strategies for Varia- ity and Reliability, New York: American Management
tion Reduction,” Quality Engineering, 10, 125-136. Association.
Steiner S.H and Mackay, R J (2005). Statistical Engineering: An Tukey, J W (1959). “A Quick, Compact, Two-sample Test to
Algorithm for Reducing Variation in Manufacturing Processes, Duckworth’s Specifications,” Technometrics, 1, 31-48.
Milwaukee: Quality Press. Verma, A K; Srividya, A; Mannikar, A V; Pankhawala, V A
Steiner, S H; MacKay, R J and Ramberg, J S (2008). “An Over- and Rathanraj, K J (2004). “Shainin Method: Edge over
view of the Shainin System for Quality Improvement.” other DOE techniques,” Engineering Management Confer-
Quality Engineering, 20(1), 6-99. ence 2004 Proceedings, IEEE International, 3(18-21), 1110-
1113.
“Shainin Techniques,” http://www.qsconsult.be/ESTShainin.
htm. Wang, X and Ren, H (2007). “Vehicle Power-train Noise Re-
finement Using Taguchi Method,” International Journal of
Thomas, A J and Anthony, J (2005). “A Comparative Analysis
Vehicle Noise and Vibration, 3(3), 286-301.
of the Taguchi and Shainin DOE Techniques in an Aero-
space Environment,” International Journal of Productivity Zeigel, E R (2001). A Review of World Class Quality, 2nd Edi-
and Performance Management, 54(8), 658-678. tion by K Bhote and A Bhote, Technometrics, Volume 43,
112-113.
Acknowledgements. The authors express thanks and are indebted to Mr. Sandeep Mathur, GM, Corporate Quality, Phoenix
Lamps Limited and Mr. Muneesh Babu and other executives of the Quality Control Department of Phoenix Lamps Limited, for
sharing crucial information contained in this case. No part of this article may be used without prior permission of the authors
and the company.
Sunil Sharma has been a Senior Reader in the Production & Anuradha R Chetiya is a Lecturer in the Department of Statis-
Operations Management Area at the Faculty of Management tics, Ramjas College, University of Delhi. Prior to this, she had
Studies (FMS), University of Delhi, for about two decades. He been associated with the Department of Statistics, Lady Shri
received his Ph.D. in Total Quality Management from the same Ram College as a Lecturer. She completed her M.Phil in the
institution prior to which he had completed his MBA and area of Sample Surveys from the University of Delhi and is
M.Tech. He specializes in TQM, TPM, and Supply Chain Man- currently pursuing her Ph.D. from the Faculty of Management
agement in which areas he has presented papers at many in- Studies (FMS), University of Delhi. She has presented papers
ternational and national conferences of which at least three at a number of conferences on Six Sigma methodology and its
being at the Indian Institute of Management, Ahmedabad. He implementation on which her research is also based.
received the UGC Research Award in 2003-05 to work on Sup-
e-mail: anuradha_rc@hotmail.com
ply Chain Management Practices in India based on which he
is currently authoring a book.
e-mail: ssharma@fms.edu