Loading Purplepass...
What to Do When it's Not a Bell Curve
Presented By Compliance Training Panel
Friday, May 18th at 1:00pm EST
Online sale ends: 05/18/18 at 12:45pm EST
Online Event
Bethesda, MD 20817
= series =
Buy Tickets
Talent
William A. Levinson Description
Statistical process control (SPC), process performance indices (Ppk), and acceptance sampling by variables (ANSI/ASQ Z1.9, or formerly MILSTD 414) rely on the assumption that the process data follow the normal or bell curve distribution. This distribution is far more common in textbooks than in the real world. Generally accepted and off the shelf methods are however available for SPC and process performance analysis for nonnormal distributions.
While we are not aware of formal sampling plans for nonnormal distributions, it is however possible to get a confidence limit for the nonconforming fraction in a homogeneous production lot. As an example, we can be 95% confident that the nonconforming fraction is no greater than a certain percent depending on the sample data and sample size. Objective : Attendees will learn the generally accepted, and off the shelf, methods for using SPC and carrying out process performance studies for nonnormal distributions, and also confidence limits for the nonconforming fraction in a homogenous production lot. The latter is a potential alternative for nonnormal distributions where ANSI/ASQ Z1.9 cannot be used. The traditional Shewhart control chart has a 0.00135 (0.135%) false alarm risk at each control limit, but this assumes that the data follow a normal distribution. When the distribution is nonnormal, the risk may be considerably higher, especially when there is a onesided specification for the quality characteristic in question. This is especially true when there is a physical limit, such as the fact that it is impossible to get less than zero impurities, particles, trace metal concentrations, and so on. If the bell curve extends below zero, it models a physically impossible situation—and the population fraction in question will instead be toward the upper control limit. If the actual distribution is known, however, control charts can be set up that have the traditional false alarm risk. If SPC uses sample averages, the Central Limit Theorem will mitigate against the effects of nonnormality, but individual measurements rather than averages are in or out of specification. This means we must identify the correct underlying distribution to perform a valid process performance study. If we assume wrongly that the distribution is normal, the estimated nonconforming fraction can be off by orders of magnitude; a purported Six Sigma process might not even be capable. Again, however, generally accepted and off the shelf methods are available to handle these situations. ANSI/ASQ Z1.9 relies explicitly on the assumption that the measurements in the production lot follow the normal distribution. If they do not, the producer and customer cannot rely on the standard to assure the specified level of quality. It is however possible to calculate a 90%, 95%, or whatever is desired confidence limit for the nonconforming fraction based on (1) the sample data and (2) the sample size if we know the underlying statistical distribution. Areas Covered in the Session : 1.Statistical Process Control *SPC charts for nonnormal distributions can be set up by calculating the 0.00135 and 0.99865 quantiles of the distribution in question, and setting the control limits accordingly. The false alarm risks will then be identical to those of a traditional Shewhart control chart. *Traditional Shewhart charts might be usable for sample averages due to the Central Limit Theorem, which says averages for large enough sample sizes will follow a roughly normal distribution regardless of the underlying distribution. 2.Process Performance Studies *The traditional calculations for capability and performance indices rely on the assumption that the process follows a normal or bell curve distribution. Application of the same mathematical formulas to nonnormal data will deliver grossly inaccurate results. *Off the shelf methods are however available with which to calculate meaningful performance indices for these processes. If for example a nonnormal process has an estimated nonconforming fraction of 0.00135 beyond its upper specification limit, its PPU equals 1 (the same as for a normally distributed process with the same nonconforming fraction). This approach is described in the Automotive Industry Action Group's SPC manual. Minitab and StatGraphics perform the necessary calculations automatically. 3.Acceptance Sampling 4.ANSI/ASQ Z1.9 (formerly MILSTD 414) relies on the assumption that the quality characteristic have a normal distribution. We cannot use this standard when this requirement is not met. 5.Not much literature is available for similar sampling plans for nonnormal distributions. It is however possible to calculate an upper confidence limit for the nonconforming fraction in a homogenous lot that depends on (1) the underlying distribution, (2) the sample data, and (3) the sample size. Commercially available packages like StatGraphics and Minitab will do this automatically. *The traditional application is reliability, where we want to be (for example) 95% sure that 99% or more of the population will survive more than a certain number of hours. The same methods can however be used to state (for example) that we are 95% sure that 1% or less of the population will be outside a specification limit. Who Will Benefit: Manufacturing and quality engineers and technicians About Speaker: William A. Levinson, P.E., FASQ, CFPIM, is the owner of Levinson Productivity Systems PC. He holds professional certifications from the American Society for Quality, APICS, and Society of Manufacturing Engineers. Organizer: Compliance Training Panel Website: www.compliancetrainingpanel.com/Webinar/Live Contact: support@compliancetrainingpanel.com Phone: 8442165230 
Presented By
1:00pm to 2:00pm
General Admission: $179.00
21+
200 8442165230 UPCOMING EVENTS
PAST EVENTS
Thursday, May 10th
Online Event Past Event
