Six sigma green belt

Courtesy: Six sigma green belt

Tools and methods

Within the individual phases of a DMAIC or DMADV project, Six Sigma uses many established quality-management tools that are also used outside Six Sigma. The following table shows an overview of the main methods used.

• 5 Whys
• Statistical and fitting tools
  • Analysis of variance
  • General linear model
  • ANOVA Gauge R&R
  • Regression analysis
  • Correlation
  • Scatter diagram
  • Chi-squared test
• Axiomatic design
• Business Process Mapping/Check sheet
• Cause & effects diagram (also known as fishbone or Ishikawa diagram)
• Control chart/Control plan (also known as a swimlane map)/Run charts
• Cost–benefit analysis
• CTQ tree
• Design of experiments/Stratification
• Histograms/Pareto analysis/Pareto chart
• Pick chart/Process capability/Rolled throughput yield
• Quality Function Deployment (QFD)
• Quantitative marketing research through use of Enterprise Feedback Management (EFM) systems
• Root cause analysis
• SIPOC analysis (Suppliers, Inputs, Process, Outputs, Customers)
• COPIS analysis (Customer centric version/perspective of SIPOC)
• Taguchi methods/Taguchi Loss Function
• Value stream mapping
• Role of the 1.5 sigma shift
• Experience has shown that processes usually do not perform as well in the long term as they do in the short term. As a result, the number of sigmas that will fit between the process mean and the nearest specification limit may well drop over time, compared to an initial short-term study. To account for this real-life increase in process variation over time, an empirically based 1.5 sigma shift is introduced into the calculation. Mikel Harry, the creator of Six Sigma, based the 1.5 sigma shift on the height of a stack of discs. He called this “Benderizing”. He claimed that based on his stack, all processes shift 1.5 sigma every 50 samples. According to this idea, a process that fits 6 sigma between the process mean and the nearest specification limit in a short-term study will in the long term fit only 4.5 sigma – either because the process mean will move over time, or because the long-term standard deviation of the process will be greater than that observed in the short term, or both.
• Hence the widely accepted definition of a six sigma process is a process that produces 3.4 defective parts per million opportunities (DPMO). This is based on the fact that a process that is normally distributed will have 3.4 parts per million outside the limits, when the limits are six sigma from the “original” mean of zero and the process mean is then shifted by 1.5 sigma (and therefore, the six sigma limits are no longer symmetrical about the mean). The former six sigma distribution, when under the effect of the 1.5 sigma shift, is commonly referred to as a 4.5 sigma process. The failure rate of a six sigma distribution with the mean shifted 1.5 sigma is not equivalent to the failure rate of a 4.5 sigma process with the mean-centered on zero. This allows for the fact that special causes may result in a deterioration in process performance over time and is designed to prevent underestimation of the defect levels likely to be encountered in real-life operation.
• The role of the sigma shift is mainly academic. The purpose of six sigma is to generate organizational performance improvement. It is up to the organization to determine, based on customer expectations, what the appropriate sigma level of a process is. The purpose of the sigma value is as a comparative figure to determine whether a process is improving, deteriorating, stagnant or non-competitive with others in the same business. Six Sigma (3.4 DPMO) is not the goal of all processes.
• The table below gives long-term DPMO values corresponding to various short-term sigma levels.
• These figures assume that the process mean will shift by 1.5 sigma toward the side with the critical specification limit. In other words, they assume that after the initial study determining the short-term sigma level, the long-term C_pk value will turn out to be 0.5 less than the short-term C_pk value. So, now for example, the DPMO figure given for 1 sigma assumes that the long-term process mean will be 0.5 sigma beyond the specification limit (C_pk = –0.17), rather than 1 sigma within it, as it was in the short-term study (C_pk = 0.33). Note that the defect percentages indicate only defects exceeding the specification limit to which the process mean is nearest. Defects beyond the far specification limit are not included in the percentages.
• The formula used here to calculate the DPMO is thus{\displaystyle {\text{DPMO}}=1,000,000\cdot (1-\phi ({\text{level}}-1.5))}