2.1 Six Sigma project selection.
Project benefits linked directly to the organization’s bottom line
Rigorous application of data analysis and statistical tools
An extremely high standard for quality
In this management framework, quality is no longer relegated to the quality department, nor is it reserved only for the shop floor. Each facility, each department, and each employee plays a part in improving quality.
In larger companies with an established Six Sigma program, a high‐level steering committee chooses Six Sigma projects that align with and help advance the company’s strategic goals. These strategic goals are derived from customer requirements and upper management’s overall business strategy. The relationship among these elements is illustrated in Figure 2.1. These projects are completed by cross‐functional teams, and the benefits are reported in terms of defect reduction and, especially, dollar savings.
The Six Sigma philosophy also places an emphasis on measurement. Decisions are based on data, not on company folk wisdom or gut feel. In addition, there is a relentless emphasis on reducing variation, driven in large part by an extremely high standard of quality in which virtually no defects are produced.
2.2.2 Six Sigma as a Systemic Approach to Problem Solving
The second definition of Six Sigma refers to a systematic approach to problem‐solving. The emphasis in Six Sigma is on solving process problems. A process is a series of steps designed to produce products and/or services.
As shown in Figure 2.2, the inputs to a process may include materials, people, or information. These inputs flow through the steps of the process, which produces a product or service as a final output. The concept can be applied to any industry or function. A manufacturing process may take raw materials and transform them into a finished product. In a front‐office process, invoices may go through process steps that then create vendor payments. A physician may order a series of tests, which finally leads to a diagnosis and treatment.
The Six Sigma methodology is driven by team projects that have a clearly defined purpose and specific goals. The projects concentrate on improving processes and have relatively short durations, with the majority completed within two to nine months. Project goals generally focus on reducing variation in a process and consequently reducing defects. Teams work together to accomplish project goals by following problem‐solving approach or five defined phases: Define, Measure, Analyze, Improve, and Control, (DMAIC, pronounced “duh may’ ik”), as shown in Figure 2.3.
Figure 2.2 Flow chart of a process.
Figure 2.3 The DMAIC cycle.
In the Define phase, a team sifts through customer feedback and product performance metrics to craft project problem and goal statements and establish baseline measures. Labor, material, and capital resources required by the project are identified, and a rough timeline for project milestones is created. This information is collected into a project charter that is approved by upper management.
During the Measure phase, the team identifies important metrics and collects additional data to help describe the nature of the problem.
In the Analyze phase, the team uses statistical and graphical techniques to identify the variables that are major drivers of the problem. In this stage, root causes of the problem are identified.
In the Improve phase, the team identifies ways to address the root cause(s) and prioritizes the potential solutions. Then, changes to the process are designed, tested, and then implemented.
In the final Control phase, the team works to create a plan to prevent the newly improved process from backsliding to previous levels of defects. Mechanisms for ongoing monitoring and control of key variables are also established at this point. During the project wrap‐up, the team’s success is celebrated, and the lessons that the team learned during the project are shared throughout the company so that other teams can benefit from their discoveries.
2.2.3 Six Sigma as a Statistical Standard of Quality
The third definition of Six Sigma refers to a level of quality that produces very few defects in the long term. With this definition, Six Sigma is often written using the numeral 6 and the Greek letter sigma: 6σ.
Bill Smith devised this standard of quality at Motorola in 1986. According to Smith’s definition, over the long run, a process running at a 6σ level will produce 3.4 defects per million opportunities (DPMO). To achieve this extremely high level of quality, a process must produce outputs that consistently meet the target specifications. Producing outputs with very small variability around the target is the key to achieving Six Sigma quality. With such tight control over variability, even if the process drifts from the target over time, the output will still meet specifications and achieve the 3.4 DPMO standard.
Figure 2.4 The standard normal distribution curve.
As might be expected given this extremely high standard for quality, most processes are not running at a 6σ quality level. In fact, in most organizations, processes are running at the 3σ level, which translates into about 67,000 DPMO.
2.2.3.1 Statistical Basis for Six Sigma
The Six Sigma standard of quality has its basis in normal distribution theory (see Figure 2.4). We assume that the quality characteristic of interest – say, the diameter of a metal shaft – is normally distributed. The corresponding engineering specifications are assumed to be symmetric, and the process is centered at the specification target value.
For a centered process, 6σ quality is achieved when the lower and upper specifications map to ± six standard deviations from the mean, as shown in Figure 2.5. The centered process would produce approximately 2.0 defects per billion opportunities.
We then assume that no matter how well our process currently meets specifications, in the long run, the output will drift based on factors such as machine wear, incoming material variation, supplier changes, and operator variability. The assumption in Six Sigma is that even a well‐behaved process will drift from the target, perhaps by as much as 1.5 standard deviations. By applying this 1.5 sigma shift to a centered process, the rationale is that companies can gain a more realistic view of the quality level their customers will experience over the
