Six Sigma Demystified 2nd Edition

By Paul Keller

The McGraw-Hill Companies, Inc.

Copyright © 2011 The McGraw-Hill Companies, Inc.
All rights reserved.
ISBN: 978-0-07-174679-3

Contents

IntroductionPart 1 Preparing for DeploymentChapter 1 Deployment StrategyChapter 2 Developing the training and Deployment planChapter 3 Focusing the DeploymentPart 2 DMAIC MethodologyChapter 4 Define StageChapter 5 Measure StageChapter 6 Analyze StageChapter 7 Improve StageChapter 8 Control StagePart 3 Six Sigma ToolsFinal ExamAnswers to Quizzes and Final ExamAppendices1. Area under the Standard Normal Curve2. Critical Values of the t Distribution3. Chi-Square Distribution4. F Distribution (α = 1%)5. F Distribution (α = 5%)6. Control Chart Constants7. Table of d*₂ Values8. Capability Index to Sigma Level Conversion9. Estimating Sigma Using Long-Term DPMO (from Field Data)10. Durbin-Watson Test BoundsGlossaryReferencesIndex

Excerpt

CHAPTER 1

Deployment Strategy

What Is Six Sigma?

Sigma (σ) is the Greek letter used by statisticians to denote the standarddeviation for a set of data. The standard deviation provides an estimate of thevariation in a set of measured data. A stated sigma level, such as Six Sigma, isused to describe how well the process variation meets the customer’srequirements.

Figure 1.1 illustrates the Six Sigma level of performance for a stableprocess. The process data are represented by the bell-shaped distribution shown.Using the calculated value of the standard deviation (σ), the distancefrom the process centerline to any value can be expressed in sigma units. Forexample, consider the teller station at a bank whose average customer wait time(or time in queue) is 7.5 minutes with a standard deviation of the wait timecalculated as 1 minute. Six standard deviations, or 6?, from the average is 1.5minutes (in the negative direction) and 13.5 minutes (in the positivedirection).

Separately, through the use of customer surveys, focus groups, or simplefeedback, customer requirements may have been established for the process. Inthis case, the process is likely to have only an upper specification limitdefined by the customers; there is no minimum limit to desirable wait times.

If this upper specification coincides exactly with the plus 6σ level(i.e., 13.5 minutes), then the process is at the Six Sigma level of performance.The implication is that the customer wait time will exceed the customerrequirements only a very small percentage of the time. Similarly, if the maximumallowable customer wait time is 10 minutes, then the process would be operatingat only a 2.5σ level of performance, indicating an increased risk ofcustomers exceeding this maximum wait time.

Although the normal distribution tables discussed later in this text indicatethat the probability of exceeding 6 standard deviations (i.e., z = 6) istwo times in a billion opportunities, the accepted error rate for Six Sigmaprocesses is 3.4 defects per million opportunities (DPMO). Why the difference?When Motorola was developing the quality system that would become Six Sigma, anengineer named Bill Smith, considered the father of Six Sigma, noticed thatexternal failure rates were not well predicted by internal estimates. Instead,external defect rates seemed to be consistently higher than expected. Smithreasoned that a long-term shift of 1.5σ in the process mean would explainthe difference. In this way, Motorola defined the Six Sigma process as one thatwill achieve a long-term error rate of 3.4 DPMO, which equates to 4.5 standarddeviations from the average. While this may seem arbitrary, it has become theindustry standard for both product and service industries.

These concepts have been applied successfully across a broad range of processes,organizations, and business sectors with low and high volumes and millions orbillions in revenue and even in nonprofit organizations. Any process canexperience an error, or defect, from a customer’s point of view. The error maybe related to the quality, timeliness, or cost of the product or service. Oncedefined, the Six Sigma techniques can be applied to methodically reduce theerror rate to improve customer satisfaction.

Using the curve shown in Figure 1.2 (Keller, 2001), any known processerror rate can be converted directly to a σ level. Most companies,including those with typical total quality management (TQM)-type programs,operate in the 3σ to 4σ range based on their published defect rates.In Figure 1.2, airline baggage handling, order processing, tech centerwait time, and flight on-time performance fall in the general area from 3σto 4σ

Notice that the y axis, representing DPMO, is logarithmically scaled. As sigmalevel is increased, the defects per million opportunities decreasesexponentially. For example, in moving from 3σ to 4σ, the DPMO dropsfrom 67,000 to 6,500 and then to just over 200 at 5σ.

Moving from left to right along the curve in Figure 1.2, the qualitylevels improve. Companies operating at between 2σ and 3σ levelscannot be profitable for very long, so, not surprisingly, only monopolies,government agencies, or others with captive customers can afford to operate atthese levels.

It’s clear that significant improvement in customer satisfaction is realized inmoving from 3σ to 4σ. Moving beyond 4σ or 5σ involvessqueezing out every last drop of potential improvement. Six Sigma is truly asignificant achievement, requiring what Joseph Juran termed breakthroughthinking (Juran and Gryna, 1988).

There is some criticism of the DPMO focus, specifically with the definition ofan opportunity. In counting opportunities for error in a deposittransaction at a bank, how many opportunities are there for error? Is eachcontact with a customer a single opportunity for error? Or should all thepossible opportunities for error be counted, such as the recording of anincorrect deposit sum, providing the wrong change to the customer, depositing tothe wrong account, and so on? This is an important distinction becauseincreasing the number of potential opportunities in the denominator of the DPMOcalculation decreases the resulting DPMO, increasing the sigma level.

Obviously, an artificially inflated sigma level does not lead to higher levelsof customer satisfaction or profitability. Unfortunately, there will always besome who try to “game” the system in this manner, which detracts from the SixSigma programs that estimate customer satisfaction levels honestly.

Since DPMO calculations can be misleading, many successful Six Sigma programsshun the focus on DPMO. In these programs, progress is measured in other terms,including profitability, customer satisfaction, and employee retention.Characteristics of appropriate metrics are discussed in more detail later inthis section.

The financial contributions made by Six Sigma processes are perhaps the mostinteresting to focus on. The cost of quality can be measured for anyorganization using established criteria and categories of cost. In Figure1.3, the y axis represents the cost of quality as a percentage of sales. Fora 2σ organization, roughly 50 percent of sales is spent on non-value-addedactivities. It’s easy to see now why for-profit organizations can’t exist at the2σ level.

At 3σ to 4σ, where most organizations operate, an organizationspends about 15 to 25 percent of its sales on “quality-related” activities. Ifthis sounds high, consider all the non-value-added costs associated with poorquality: quality assurance departments, customer complaint departments, returns,and warranty repairs. These associated activities and costs are sometimesreferred to as the “hidden factory,” illustrating the resource drain they placeon the organization.

For many organizations, quality costs are hidden costs. Unless specific qualitycost identification efforts have been undertaken, few accounting systems includeprovision for identifying quality costs. Because of this, unmeasured qualitycosts tend to increase. Poor quality affects companies in two ways: higher costand lower customer satisfaction. The lower satisfaction creates price pressureand lost sales, which results in lower revenues. The combination of higher costand lower revenues eventually brings on a crisis that may threaten the veryexistence of the company. Rigorous cost of quality measurement is one techniquefor preventing such a crisis from occurring.

It’s not uncommon for detailed quality audits to reveal that 50 percent of thequality costs go unreported to management, buried in general operating costs.Often these costs are considered “the cost of doing business” to ensure a high-quality product or service to the customer. Reworking, fine-tuning, touch-ups,management approvals, next-day deliveries to compensate for delayed or failedprocesses, and fixing invoice errors are all non-value-added costs that may gounreported.

As an organization moves to a 5σ level of performance, its cost of qualitydrops to around 5 percent of sales. The Six Sigma organization can expect tospend between 1 and 2 percent of sales on quality-related issues.

How are these cost savings achieved? As a company moves from 3σ to4σ and then to 5σ, its quality costs move from “failure costs” (suchas warranty repairs, customer complaints, and so on) to “prevention costs” (suchas reliability analysis in design or customer surveys to reveal requirements).Consider the increased costs incurred when customers detect problems. A commonrule of thumb is that an error costing $1 to prevent will cost $10 to detect andcorrect in-house and $100 to remedy if the customer detects it. These orders ofmagnitude provide an incentive to move toward error prevention.

The cost of quality also drops quickly as dollars that go to waste in a 3?organization (owing to failure costs) go directly to the bottom line in a SixSigma organization to be reinvested in value-added activities that boostrevenue. Thus, while the 3? organization is forever in “catch-up” or”firefighting” mode, the Six Sigma organization is able to fully use itsresources for revenue generation. This infusion of capital helps the sales sideof the equation, so the cost of quality as a percentage of sales (shown inFigure 1.3) drops more quickly.

Differences Between Six Sigma and Total Quality Management (TQM)

There are four key differences between a Six Sigma deployment and TQM-styleimplementations (Keller, 2001):

• Project focus and duration. Six Sigma deployment revolves around SixSigma projects. Projects are defined that will concentrate on one or more keyareas: cost, schedule, and quality. (Note that other possible considerations,such as safety or product development, could be restated in terms of cost,schedule, and/or quality, as will be described later in this book.) Projects maybe developed by senior leaders for deployment at the business level or developedwith process owners at an operational level. In all cases, projects are linkeddirectly to the strategic goals of the organization and approved for deploymentby high-ranking sponsors.

The project sponsor, as a leader in the organization, works with the projectleader (usually a black belt) to define the scope, objective(s), anddeliverables of the project. The sponsor ensures that resources are availablefor the project members and that person builds support for the project at upperlevels of management as needed. All this is documented in a project charter,which serves as a contract between the sponsor and the project team.

The scope of a project is typically set for completion in a three- to four-monthtime frame. Management sets criteria for minimal annualized return on projects,such as $100,000. The structure of the project and its charter keep the projectfocused. The project has a planned conclusion date with known deliverables. Andit has buy-in from top management. These requirements, together with the SixSigma tools and techniques, build project success.

• Organizational support and infrastructure. As shown in the nextsection, a proper Six Sigma deployment provides an infrastructure for success.The deployment is led by the executive staff, who use Six Sigma projects tofurther their strategic goals and objectives. The program is actively championedby middle- and upper-level leaders, who sponsor specific projects in theirfunctional areas to meet the challenges laid down by their divisional leaders(in terms of the strategic goals). Black belts are trained as full-time projectleaders in the area of statistical analysis, whereas process personnel aretrained as green belts to assist in projects as process experts. Master blackbelts serve as mentors to the black belts and deployment experts to themanagerial staff.

• Clear and consistent methodology. A somewhat standard methodology hasbeen developed for Six Sigma projects, abbreviated as DMAIC (pronounced”dah-may-ick”), an acronym for the define, measure, analyze, improve, andcontrol stages of the project. This discipline ensures that Six Sigma projectsare clearly defined and implemented and prevents the recurrence of issues.

• Top-down training. A properly structured deployment starts at the top,with training of key management. Six Sigma champions, consisting of executive-level decision makers and functional managers, are necessary to align the SixSigma program with the organization’s business objectives through projectsponsorship and to allocate resources to project teams. Without committedchampions supporting them, black belts lack the authority, resources, andbusiness integration necessary for project success.

The result of a properly implemented Six Sigma deployment is data-drivendecision making at all levels of the organization that is geared towardsatisfying critical needs of key stakeholders.

Six Sigma deployment doesn’t cost, it pays. With minimum savings of $100,000 perproject, the Six Sigma training projects will provide financial returns that farexceed the cost of the training. This “reward as you go” deployment strategy hasproven beneficial to organizations of all sizes.

If you’re still unsure whether a Six Sigma program is the right path for yourorganization, consider the impact on market share if your closest competitorimplemented a Six Sigma program and you didn’t.

Six Sigma and Lean

A proper Six Sigma deployment includes use of the lean tools and methods. Inthis regard, there is no difference between a properly developed Six Sigmaprogram and a lean Six Sigma program. Six Sigma (aka lean Six Sigma) is adeployment strategy for implementing value-added improvement projects alignedwith an organization’s business needs. These focused projects target critical-to-quality(CTQ), critical-to-schedule (CTS), and/or critical-to-cost (CTC)opportunities within an organization. Six Sigma uses a variety of tools andmethods, including statistical (i.e., enumerative stats, statistical processcontrol, and designed experiments), problem-solving, consensus-building, andlean tools. A given project may not use all the tools, yet most organizationsfind that they need most of the tools at any given time. Lean provides essentialmethods to define value and waste to improve an organization’s responsiveness tocustomer needs. As such, the lean methods provide a critical means ofaccomplishing the Six Sigma goals. Similarly, the lean methods require the useof data, and statistics provide the necessary methods for data analysis. It’sunfortunate that some lean advocates and some lean Six Sigma programs do notstress the critical importance of the statistical tools in their analysisbecause this lack of rigor will prevent lean-focused projects from realizingtheir full potential.

Elements of a Successful Deployment

Jack Welch, former CEO of General Electric, said: “This is not the program ofthe month. This is a discipline. This will be forever” (Slater, 1999).

Six Sigma is primarily a management program. For many organizations, it willfundamentally change the way they operate. It must, if it is to achieve thelevels of improvement shown earlier. Consider that moving from 3σ to4σ means a 91 percent reduction in defects; from 4σ to 5σ, anadditional 96 percent; and from 5σ to Six Sigma, a 99 percent furtherreduction. Without strong management and leadership, the time, effort, andexpertise of the Six Sigma project team will be wasted, and results will not beachieved.

Program success is based on the following four factors, presented in order ofimportance:

• Support and participation of top management

• Sufficient resource allocation to improvement teams

• Data-driven decision making using DMAIC

• Measurement and feedback of key process characteristics

Management Support and Participation

A successful Six Sigma program must be integrated into the organization’sbusiness strategy. Active participation by leaders in the organization willensure program survival.

As with most initiatives he launched as CEO of General Electric, Jack Welch wasnearly fanatical about the Six Sigma program. In a January 1997 meeting, only ayear after officially announcing the inception of the program to his managers,he challenged them:

You’ve got to be passionate lunatics about the quality issue…. This has to becentral to everything you do every day. Your meetings. Your speeches. Yourreviews. Your hiring. Every one of you here is a quality champion or youshouldn’t be here…. If you’re not driving quality, you should take your skillselsewhere. Because quality is what this company is all about. Six Sigma mustbecome the common language of this company…. This is all about better businessand better operating results. In 1997, I want you to promote your best people.Show the world that people who make the big quality leadership contributions arethe leaders we want across the business [Slater, 1999].

To get the most from the endeavor, management must actively support the SixSigma initiative. Welch urged management to find opportunities to motivateemployees to use Six Sigma in meetings, speeches, reviews, and hiring.

Jack Welch further challenged his executive vice presidents by tying 40 percentof their bonuses to specific bottom-line improvements from their Six Sigmainitiatives (Slater, 1999). He realized that it was critical to move beyond merewords and to demonstrate commitment with leadership and results. Thisparticipation from senior management, through integration with the company’sbusiness strategy and practices, marked a key departure from run-of-the-mill TQMinitiatives, where leadership was delegated to departments with little authorityor few resources.

The key priorities for management leadership include

• Define objectives and goals of the program. How is program successmeasured?

(Continues…)
(Continues…)Excerpted from Six Sigma Demystified 2nd Edition by Paul Keller. Copyright © 2011 by The McGraw-Hill Companies, Inc.. Excerpted by permission of The McGraw-Hill Companies, Inc..
All rights reserved. No part of this excerpt may be reproduced or reprinted without permission in writing from the publisher.
Excerpts are provided by Dial-A-Book Inc. solely for the personal use of visitors to this web site.