This action might not be possible to undo. Are you sure you want to continue?
Statistical Process Control: An Analysis in Quality Management
Stephanie Thomas Keller Graduate School of Management Managing Quality_GM588 Professor Chester Legenza June 6, 2010
Author Note Correspondence concerning this paper should be addressed to Stephanie Thomas, 1885 Manor Drive, Apt. A; Union, NJ, 07083, email@example.com, 917-291-0178
Its methods and tools can be effectively employed in industries such as Customer Service. An example of this is a manufacturing machine due to erroneous specification is thrown offline.STATISTICAL PROCESS CONTROL: AN ANALYSIS IN QUALITY MANAGEMENT Introduction Statistical Process Control is a quality assurance organizing system primarily utilized in manufacturing. after WWII. The variation suggests there is abnormal occurrence to the process. Deming’s contribution is credited for introducing the methodology to the Japanese. by Dr. Assignable causes are unexpected problems adversely affecting processes and will cause them to go out of control. Hospitals. 2009)This maturity model was developed by in the 1920’s. which causes defective product output. normal and assignable. and Media Services. and expanded by Dr. while minimizing production output waste. Normal causes of process variation can be defined as changes due to common causes (random variation in processes existing in all processes and does not require special attention). Its major philosophy of evaluation of process variation and its causes ensures product efficiency. Its premise is the identification of process variation and characteristic measurement through evaluating two classes of variation causes. Dr. Fire and Police Departments. due to the utilization of seasonal employees. Normal causes could be a temporary slowdown in production. and should be eradicated. . 2 (Raczynski. W Edwards Deming. Walter Sheward of Bell Laboratories.
and are essential in maintaining continuous improvement efforts in managing quality throughout the process life cycle.JPG6/5/2010 2:04:19 PM . Control Charts and Histograms are the more common of these tools and serves as a visual representation in monitoring the extent to which products meet specifications.) http://www.com/Opening%20X-Bar%20R2. (Quinn-Curtis Inc. A change to normal process variance is demonstrated by shifts within control limits.STATISTICAL PROCESS CONTROL: AN ANALYSIS IN QUALITY MANAGEMENT 3 Certain improvement tools are used in the monitoring and controlling of SPC. and assist the adjuster to where the process should be controlled.quinn-curtis. It detects whether a process is statistically stable. These shifts will show its severity.
. have extended their SPC efforts with Six Sigma programs. For visually displaying data..STATISTICAL PROCESS CONTROL: AN ANALYSIS IN QUALITY MANAGEMENT 4 Those applying SPC to industrial organizations. Many corporations.g. however. For identifying assignable causes. in general. (DACS. For identifying processes that are out of control. in a pie chart. Six Sigma programs use the “Seven Tools of Quality” (Table 5). SPC is not intended to lower process variation resulting from natural causes. e. To identify the 20% of the modules which yield 80% of the issues. The focus of SPC is on removing variation caused by assignable causes. Typically. As defined here. For identifying correlation and suggesting causation. To identify central tendencies and any skewing to one side or the other. Six Sigma provides continuous process improvement and attempts to reduce the natural variation in processes. 2010) Tool Check Sheet Histogram Pareto Chart Cause and Effect Diagram Scatter Diagram Control Chart Graph Table 5: The Seven Tools of Quality Example of Use To count occurrences of problems. The Shewhart Cycle (Figure 4) is a fundamental idea for continuous process improvement. have built process improvements on top of SPC.
e.STATISTICAL PROCESS CONTROL: AN ANALYSIS IN QUALITY MANAGEMENT 5 Table 4: Some Applications of Statistics in Software Engineering Phase Use of Statistics Requirements Design Coding Testing Specify performance goals that can be measured statistically. Pareto analysis to identify fault-prone modules. The study of SPC and its effective utilization well enable these organizations to accomplish the stabilization of product development. Reliability models can be applied. Coverage metrics provides attributes. or any output production process. et. Statistical control charts applied to inspections. al.g. no more than 50 total field faults and zero critical faults with 90% confidence. 1993] Literature Review The Significance of SPC Examination The driving force of successful organizations is their ability to ensure the highest possible level of customer satisfaction through performance improvement. Benefits of SPC are: • • • • • Signals when a problem with the process has occurred Detects assignable causes of variation Accomplishes process characterization Reduces need for inspection Monitors process quality . customer services. Design of experiments useful in creating test suites.. Based on [Dalal. Statistical usage testing is based on specified operational profile. Use of design of experiments in making design decisions empirically.
SPC provides real time analysis to establish controllable process baselines. and dynamically improve process capabilities.STATISTICAL PROCESS CONTROL: AN ANALYSIS IN QUALITY MANAGEMENT • Provides mechanism to make process changes and track effects of those changes(Thompson) 6 Once a process is stable (assignable causes of variation have been eliminated). in that currently its tools and procedures are sought by many organizations to eliminate waste and create effective process procedures. and focus business on areas needing improvement. 2000) These benefits of SPC cannot be obtained immediately by all organizations. even in our current business society. It requires a climate in which personnel are not punished when problems are detected. SPC incorporates a wide range of real time analysis to assist by establishing controllable process baselines. SPC requires defined processes and a discipline of following them. communication of value and results of processes. . insights for process improvements. something concrete. Statistical techniques provide an understanding of the business baselines. set. SPC moves away from opinion-based decision making (Radice. 1989) The study of Statistical Process Control in organizations comes from the necessity for companies that are vulnerable to process changes. provides process capability analysis with comparison to the product tolerance. and active and visible involvement. Current SPC Relevance SPC relevancy is apparent. It requires management commitment (Demmy. In management decisions. learn.
Requirements . some kind of spiral-based methodology is used over a waterfall process. see Plug-in Central. 2. This does not necessarily imply that all requirements need to be fixed before any architecture.STATISTICAL PROCESS CONTROL: AN ANALYSIS IN QUALITY MANAGEMENT For instance. This is an example of these in developing software projects. 1. its invaluably is sought after to trim the waste. IBM® Global Services Method. In Banking. For a list of available plug-ins. but it is important for the development team to understand what needs to be built. these books still provide an excellent source of best practices. In addition. design.It is important to choose the appropriate development lifecycle process to the project at hand because all other activities are derived from the process. Quality requirements are broken up into two kinds: functional . the RUP has a series of books that describe the best practices for using RUP  although if you do not choose to use RUP. There are several choices. including the Rational Unified Process (RUP). and coding are done. and eXtreme Programming (XP). It is also possible to add plugins to the RUP. Development process . in the Health and Human Services Departments SPC is seriously incorporated in placing the correct amount of services in the areas where it is most needed. Statistical Process Control Best Practices 7 In SPC. For most modern software development projects.Gathering and agreeing on requirements is fundamental to a successful project. the incorporated best practices are as diverse as the different types of organizations that have integrated the methodology. The commonly used methodologies listed above all contain guidance about how to execute the process and templates for artifacts. operate more efficiently with less personnel. Having a process is better than not having one at all. and in many cases it is less important on what process is used than how well it is executed.
Many projects fail as discussed in the introduction. Non-functional requirements describe the performance and system characteristics of the application.STATISTICAL PROCESS CONTROL: AN ANALYSIS IN QUALITY MANAGEMENT 8 and non-functional. and why. but it is often unrealized because of the additional effort required to create reusable assets. . and performance. A definitive book on the subject of use cases is by Armour and Miller . it is important to perform Object-Oriented Analysis and Design using UML.Choosing the appropriate architecture for your application is key. to EJB design patterns . Tried and true practices are called patterns and they range from the classic Gang of Four  patterns. Many times IBM is asked to review a project in trouble and we have found that the development team did not apply well-known industry architecture best practices. Design . They are valuable because they provide useful knowledge of what does not work. It is important to gather them because they have a major impact on the application architecture. There are many books on UML. For many projects.Even with a good architecture it is still possible to have a bad design. Note that Use Cases are used for non-OO projects. The study of these failures has given rise to the concept of antipatterns. Many applications are either over-designed or under-designed. A good way to avoid this type of problem is to contact IBM. Our consultants can work side by side with your team and ensure that the projects get started on the right track. but we recommend UML User Guide  and Applying UML and Patterns . design. The two basic principles here are "Keep it Simple" and information hiding. 4. Java patterns . Sun's equivalent is the Core J2EE Patterns catalog . 3. Reuse is one of the great promises of OO. See the non-functional requirements checklist on the Construx Web site. Architecture . A good way to document functional requirements is using Use Cases.
Construction of the code .IBM has extensive knowledge of the best practices and design patterns for the WebSphere product family. In projects with no development process (so-called "code and fix"). Note that even though continuous integration and unit tests have gained popularity through XP. Karl Wiegers paper on the Seven Deadly Sins of . such as Ant and JUnit. A best practice for constructing code includes the daily build and smoke test.STATISTICAL PROCESS CONTROL: AN ANALYSIS IN QUALITY MANAGEMENT Code reuse is but one form of reuse and there are other kinds of reuse that can provide better productivity gains. analysis. I recommend using standard frameworks to automate builds and testing. 7. and test. design. 9 5. Each project is different and our consultants have the experience to help you. architecture. Martin Fowler goes one step further and suggests continuous integration that also integrates the concept of unit tests and self-testing code. architecture. you can use these best practices on all types of projects. code. and test cases. Any artifact from the development process is reviewed.Construction of the code is a fraction of the total project effort. Peer reviews . 6. including plans. these tasks are also happening. design. Our experts have also published a great deal of this wisdom. including considerations for high-performance Web sites and guidelines for autonomic computing. but under the guise of programming. Other work equally important includes requirements. WebSphere application design .It is important to review other people's work. Experience has shown that problems are eliminated earlier this way and reviews are as effective or even more effective than testing. requirements. but it is often the most visible. There is still a tremendous return on investment (ROI) even if you only use the consultants for a short time because you save the costs later in the project.
It is important to establish quality priorities and release criteria for the project so that a plan is constructed to help the team achieve quality software. It is important that a defect tracking system is used that is linked to the source control . Peer reviews are helpful in trying to produce software quality at top speed. such as Rational Clearcase. There are also best practices and patterns  for configuration management. the defect arrival and fix rate can help measure the maturity of the code. As the project is coded and tested. 10. meaning that test cases are planned before coding starts. Architecture and design defects may be missed. 9. There is more to configuration management than just source control systems. Quality and defects management . Configuration management . It is an integral part of software development that needs to be planned.STATISTICAL PROCESS CONTROL: AN ANALYSIS IN QUALITY MANAGEMENT 10 Software Reviews explains the correct ways to perform peer reviews. and test cases are developed while the application is being designed and coded. and releasing distinct versions of a system. It is also important that testing is done proactively. 8. It is labor intensive and usually only catches coding defects. 11.Configuration management involves knowing the state of all artifacts that make up your system or project.Testing is usually the last resort to catch application defects. Testing . There are also a number of testing patterns that have been developed.Testing is not an afterthought or cutback when the schedule gets tight. Performance testing . One method to catch some architectural defects is to simulate load testing on the application before it is deployed and to deal with performance issues before they become problems. managing the state of those artifacts.
Our recommended bible for project management is Rapid Development by Steve McConnell . To ease the flow of problems. System operations and support . the support problem database is hooked into the application defect tracking system. 13. You need to plan for deployment and you can use a deployment checklist on the Construx Web site. Project management . Given the number of other checklists and tip sheets for project management. you plan to fail.Project management is key to a successful project. but are enhancements or rewrites of existing applications. Improving the quality of data is a complex subject outside the scope of this article. such as: "if you fail to plan. It is as important as the new application. projects using Rational ClearCase may also use Rational ClearQuest. 11 12. Many of the other best practice areas described in this article are related to project management and a good project manager is already aware of the existence of these best practices. you cannot deploy and support a new application.Most applications are not brand new. it is surprising how many project managers are not aware of them and do not apply lessons learned from previous projects. Usually the new application has better business rules and expects higher quality data.Deployment is the final stage of releasing an application for users. there are still things that can go wrong.congratulations! However. 15. 14. Data migration . Data migration from the existing data sources is usually a major project by itself.STATISTICAL PROCESS CONTROL: AN ANALYSIS IN QUALITY MANAGEMENT management system. it is possible to gauge when a project is ready to release. The support area is a vital factor to respond and resolve user problems. Deployment . By using defect tracking. For example. . If you get this far in your project ." One way to manage a difficult project is through timeboxing.Without the operations department. This is not a project for your junior programmers.
unclear specification. Measuring success . Guide to Running Software Development Projects. lack of knowledge on what to measure and how to measure in a certain process. Errors caused by lack of knowledge to prioritize processes. negative reaction of operators and middle managers. hampering the effectiveness of the SPC lead by not allowing full communication of adverse occurrences.You can measure your development process against an industry standard known as the Capability Maturity Model (CMM) from the Software Engineering Institute at Carnegie Mellon University. and inaccurate calculation of data. Segregating control charts from the people who utilize them. missing.STATISTICAL PROCESS CONTROL: AN ANALYSIS IN QUALITY MANAGEMENT 12 16. lack of documentation (charts). then you could be well on the way to achieving a higher maturity level and a successful project. These errors can affect cost inefficiency by causing a high rework level. 2006) some mistakes made during the SPC implementation and control processes are not training everyone in SPC who is responsible for maintaining quality processes. Fair (Fair. errors are made during these processes are caused by lack of information and procedure. . improper training. According to Douglass C. and using SPC for quality control without justification. If you implement the best practices described above and the guidelines in the companion article. In manufacturing. incorrect parts or incorrect processing affects the efficiency level of production. none existent documentation. lack of SPC training. 2003) Errors in Implementation and Control Generally. (Perks. and an inadequate measurement system in place. Most projects are at level 1 (initial).
EPC can maintain performance. more identifiably used in manufacturing environments and is effective in maintaining product variation. The issue of data independence in manual SPC is non-existent in CMIS because of the ability of data co-existence and integration. . Cai. However. SPC. CMIS will be able to generate charts and signals after completing a background analysis. the capability of automation allows for an abundance of data. methods and computations that are stored and delivered in record time.STATISTICAL PROCESS CONTROL: AN ANALYSIS IN QUALITY MANAGEMENT Application Demonstration This analysis gathered from a scholarly source written by (D. but cannot maintain it.Q. There may no longer be an urgent demand for engineers to fully understand the statistical background necessary in a manual SPC environment. 2001) discusses the application and effects of SPC (Statistical Process Control) combined with EPC (Engineering Process Control) in a CMIS (Computer Integrated Manufacturing System) environment. Traditional SPC methods compromised in an automated system. but cannot improve it. response time and money. The automation of SPC in an automated manufacturing environment holds many issues as well as advantages. In contrast. SPC will improve performance. This advantages save physical resources. Combining SPC and EPC methodology is complementary because. due to the ability of computation and interpretation through 13 computer automation. such as manual equation analysis and chart interpretation.
These elements are essential in maintaining a high level of quality in production. .STATISTICAL PROCESS CONTROL: AN ANALYSIS IN QUALITY MANAGEMENT Conclusion and Reflection In most SPC/EPC CMIS environments strengthens the stability overall due to: • • • • • • • more robust and effective output operational errors are minimized high level of process stability reduction of process variability reduction in system re-adjustment time outstanding computation power an abundance of available data 14 Industry and organizations that incorporate these methodologies stand a greater chance of being successful in regards to customer satisfaction and accurate throughput.
html Quinn-Curtis Inc. (2010). Demmy. 206-211.quinncurtis. M. DACS. (2009).Net Compact Framework . Cai.php Demmy.com: http://www. 1585-1590).qualitydigest. Is Statistical Process Control Applicable to Software Development Processes? .com: http://www.com: http://www. W. Retrieved from ibm. Retrieved from quinn-curtis. Inside Quality Insider. (n.). Proceedings of the IEEE National Aerospace and Electronics Conference. (2003).d. International Journal of Computer Integrated Manufacturing .(NAECON 1989.goldpractices. Fair.ibm.com/practices/spc/index. Statistical Process Control in Software Quality Assurance.com/inside/quality-insider-article/top-10-spc-mistakes# Perks. (1989). D. (2001). pp.Q.STATISTICAL PROCESS CONTROL: AN ANALYSIS IN QUALITY MANAGEMENT 15 References D. Statistical Process Control. W. Retrieved from goldpractices. C.SPC Control Chart Tools for . M. B. X.com/developerworks/websphere/library/techarticles/0306_perks/perks2. SPC in an Automated Manufacuring Environment. (pp. (2006). IBM.htm Raczynski. QCSPCChart CF . Retrieved from The Top 10 SPC Mistakes: http://www.com/QCSPCChartCFProdPage. (1989).
Steve. I. Brad. ISBN 0130648841. Larry.. Advanced Use Case Modeling. Floydd.gov: 16 http://reliability. J. Frank and Miller.. and Jacobson. Scott and Constantine. and Vlissides.com/blueprints/corej2eepatterns 10. M. Johnson. Rapid Development. Scott. ISBN 0201571684 12. ISBN 192962901X 4. Scott and Constantine. Scott and Constantine. ISBN 0201741172 14. Rumbaugh. (n. The Unified Process Elaboration Phase. ISBN 0130925691 13. Core J2EE Patterns. ISBN 0201633612 7.d. ISBN 1556159005 . E. (2000).sun.. Ambler. R. Mark. D.. and Appleton...sandia. Larman. Gamma. D. Larry. Proceedings of the 12th Annual Software Technology Conference. PDF file 9. Center for System Reliabulity. J. 11. also see http://java. Ambler. Applying UML and Patterns.gov/Manuf_Statistics/Statistical_Process_Control/statistical_process_cont rol. Marinescu. Alur.. R. Armour. Software Configuration Management Patterns.. ISBN 1929629052 3. The Unified Process Transition and Production Phases. G. Retrieved from reliability.. R. McConnell. Helm. J. IBM Redbooks. Thompson. ISBN 157820092X 5. Design Patterns. Stephen. Patterns in Java. ISBN 1929629109 2.html 1. Granville. Statistical Process Control in Level 4 and 5 Organizations Worldwide. ISBN 0471258393 8. Larry. B.sandia. EJB Design Patterns.. The Unified Process Construction Phase. Booch. ISBN 0471208310. Grand. Search for "patterns AND e-business". Berczuk. Malks.). Craig. The Unified Process Inception Phase.STATISTICAL PROCESS CONTROL: AN ANALYSIS IN QUALITY MANAGEMENT Radice. Ambler. Ambler. The Unified Modeling Language User Guide. ISBN 0201615924 6. Crupi.
This action might not be possible to undo. Are you sure you want to continue?
We've moved you to where you read on your other device.
Get the full title to continue reading from where you left off, or restart the preview.