1、BRITISH STANDARD BS 5701-1:2003 Guide to quality control and performance improvement using qualitative (attribute) data Part 1: Uses and value of attribute charts in business, industry, commerce and public service ICS 03.120.30 BS 5701-1:2003 This British Standard, having been prepared under the dir
2、ection of the Standards Policy and Strategy Committee, was published on 31 October 2003 BSI 31 October 2003 First published as BS 5701 February 1980 The following BSI references relate to the work on this British Standard: Committee reference SS/4 Draft for comment 02/400887 DC ISBN 0 580 42734 X Co
3、mmittees responsible for this British Standard The preparation of this British Standard was entrusted to Technical Committee, SS/4, Statistical process control, upon which the following bodies were represented: Association for Road Traffic Safety and Management (ARTSM) BAE Systems British Standards
4、Society (BSS) Clay Pipe Development Association (CPDA) Federation of Small Businesses (FSB) Gauge and Tool Makers Association (GTMA) General Domestic Appliances Ltd. Institute of Quality Assurance National Physical Laboratory Royal Statistical Society Amendment issued since publication Amd. No. Date
5、 CommentsBS 5701-1:2003 BSI 31 October 2003 i Contents Page Committees responsible Inside front cover Foreword ii 1S c o p e 1 2 Normative references 1 3 Terms, definitions and symbols 1 4 Qualitative (attribute) data fundamentals 1 5 Business process focus and management 7 6 Supporting techniques f
6、or effective process control and performance improvement 9 7 Relationship with Six Sigma initiatives 15 8T y p i c a l c a s e s t u d y 1 6 Annex A (informative) Base data for case study of Clause 8 25 Bibliography 27 Figure 1 Different classes of data 3 Figure 2 Process control, capability estimat
7、ion and improvement sequence 4 Figure 3 Control chart for assembly of mens briefs 6 Figure 4 Basic process model 10 Figure 5 Application of the basic process model to the actioning of a product design change 10 Figure 6 Business is made up of integrated multistage processes 11 Figure 7 Video disc pr
8、essing: flow diagram of integrated multistage process 11 Figure 8a) Illustration of the calculation of logistic capability and first run capability of a process stage 12 Figure 8b) Logistic and first run capabilities of the video disc manufacturing process 13 Figure 9 Example of Pareto diagram for p
9、aint process faults 14 Figure 10 Process cause and effect diagram for cracks in a brake disc casting 15 Figure 11 First time quality profile of trouser line 17 Figure 12 Pareto analysis by process operation 18 Figure 13 Pareto analysis by machinist/operator 18 Figure 14 Doreen lapping side seams (5.
10、3 faults per day); Total 275 faults (15 % of total faults) 19 Figure 15 Jane lapping side seams (2.1 faults per day) 19 Figure 16 Sue and Rita lapping side seams 20 Figure 17 Su barring loops 20 Figure 18 Brenda barring loops 21 Figure 19 Mandy putting the bands on 21 Figure 20 Rosalie machining ins
11、ide legs 22 Figure 21 Delia and Dorry machining inside legs 22 Figure 22 Shirley and Dawn closing the fly 23 Figure 23 Janet closing the fly 23 Figure 24 Jean closing the fly 24 Table 1 Typical business applicable characteristics 2 Table 2 Relationship between Sigma value, non-conformities per milli
12、on opportunities and percentage yield 15 Table A.1 Base data for case study of Clause 8 25BS 5701-1:2003 ii BSI 31 October 2003 Foreword BS 5701-1 demonstrates the business benefits, and the versatility and usefulness of a very simple, yet powerful, pictorial control chart method for monitoring and
13、interpreting qualitative data. This is done in a practical and largely non-statistical manner. BS 5701-1:2003 partially supersedes BS 5701:1980 and BS 2564:1955 and all four parts of BS 5701 together supersede BS 5701:1980 and BS 2564:1955, which are withdrawn. This qualitative data can range from o
14、verall business figures such as percentage profit to detailed operational data, such as percentage absenteeism, individual process parameters and product/service features. The data can either be expressed sequentially in yes/no, good/bad, present/absent, success/failure format, or as summary measure
15、s (e.g. counts of events and proportions). For measured data control charting, refer to BS 5702-1. The focus is on the application of control charts to monitoring, control and improvement. The roles of associated diagnostic, presentation and performance improvement tools, such as priority (Pareto) a
16、nalysis, cause and effect diagrams and flow charts are also shown. Its aim is to be readily comprehensible to the very extensive range of prospective users and so facilitate widespread communication, and understanding, of the method. As such, it focuses on a practical non-statistical treatment of th
17、e charting of qualitative data, presenting examples of construction and application using a simple pictorial approach. Whilst the treatment of charting of qualitative data in this part of BS 5701 is essentially at appreciation level, it is intended to provide adequate information for a gainful first
18、 application, by a typical less statistically inclined user, in many everyday situations. BS 5701-2 and BS 5701-3 provide a more rigorous, statistical approach to process control and improvement using qualitative data. BS 5701-4 deals with measuring and improving the quality of decision making in th
19、e classification process itself. A British Standard does not purport to include all the necessary provisions of a contract. Users of British Standards are responsible for their correct application. Compliance with a British Standard does not of itself confer immunity from legal obligations. Summary
20、of pages This document comprises a front cover, an inside front cover, pages i and ii, pages 1 to 27 and a back cover. The BSI copyright notice displayed in this document indicates when the document was last issued.BS 5701-1:2003 BSI 31 October 2003 1 1 Scope BS 5701-1 describes, in lay terms, the u
21、ses and value of pictorial control chart methods for enhancing the presentation and general understanding of qualitative (attribute) data arranged in a meaningful sequence. It also illustrates the supporting roles of associated business improvement tools. These include process modelling, flow charti
22、ng, prioritizing (Pareto analysis) and cause and effect diagrams. 2 Normative references The following referenced documents are indispensable for the application of this document. For dated references, only the edition cited applies. For undated references, the latest edition of the referenced docum
23、ent (including any amendments) applies. BS EN ISO 9000:2000, Quality management systems Fundamentals and vocabulary. BS ISO 3534-1, Statistics Vocabulary and symbols Part 1: Probability and general statistical terms. BS ISO 3534-2, Statistics Vocabulary and symbols Part 2: Applied statistics. 3 Term
24、s, definitions and symbols For the purposes of this part of BS 5701, the terms, definitions and symbols given in BS ISO 3534-1, BS ISO 3534-2 and BS EN ISO 9000:2000, Clause 3 apply. 4 Qualitative (attribute) data fundamentals 4.1 General In this technological age, we are awash with data. The challe
25、nge is to transform such data into meaningful information on a characteristic. There is a wide range of classes of characteristic, including: a) physical (e.g. mechanical, electrical, chemical or biological); b) sensory (e.g. relating to smell, touch, taste, sight or hearing); c) behavioural (e.g. c
26、ourtesy, honesty or veracity); d) temporal (e.g. punctuality, reliability or availability); e) ergonomic (e.g. linguistic, physiological or relating to safety); f) functional (e.g. range, speed, or rate of climb of an aircraft). Typical business application characteristics, shown in Table 1, that ar
27、e the subject of control and progressive improvement further indicate the wide scope of the subject matter of this standard.BS 5701-1:2003 2 BSI 31 October 2003 Table 1 Typical business applicable characteristics 4.2 Types of data Two general classes of data are distinguished here, measured data and
28、 attribute data. These classes can be otherwise termed continuous data and discrete data or, even, quantitative data as opposed to qualitative data. Whereas continuous data is measured on a numerical scale with a continuum of possible values, discrete data is referenced on a scale with only a set or
29、 sequence of distinct values. This standard focuses on attribute data. Attribute data are divided for convenience, into two categories, classified data and count data. With classified data, each item of data is classified as being one of a number of categories. Frequently the number of categories is
30、 two, namely a binary situation where, for instance, results are usually expressed as 0 and 1, or as, good/bad, success/failure, profit/loss, in/out, or presence/absence of a particular characteristic or feature. Data having two classes are termed “binomial” (binomial = “two names”) data. A measure
31、can be inherently binomial, e.g. where a profit or loss is made, or if someone is in or out. Sometimes it is arrived at indirectly by categorizing some other numerical measure. Take, for instance, the case where telephone calls are classified as to whether or not they last more than ten minutes or,
32、perhaps whether or not they are answered within six rings. Count data relates to counts of events where each item of data is the count of the number of particular events per given time period or quantity of product. Instances are: number of accidents or absentees per month; number of operations or s
33、orties per day; number of incoming telephone calls per minute; or number of non-conformities per unit or batch. A pictorial representation of the different types of data is shown in Figure 1. Business application Characteristic business profitability marketing market share staff absenteeism personne
34、l turnover sales enquiries results organization overall errors/faults product non-conformities service complaints incoming phone calls response delays invoicing accuracy deliveries lateness accounts overdue vehicles, machines status warranty costs over-run software errors/10 3lines computers status
35、communications clarity, timelinessBS 5701-1:2003 BSI 31 October 2003 3 4.3 Principles, objectives and rationale of the control charting of qualitative data 4.3.1 Overview Mention of the word statistics invokes a feeling of apprehension in many people. However, everyone should positively respond to,
36、understand and adopt the primary concepts of “statistical thinking”. These are as follows: 1) All work occurs in a system of interconnected processes. 2) Variation exists in all processes. 3) Elimination of special cause variation produces process stability and predictability. 4) Reduction in common
37、 cause variation is the key to continual improvement. The first concept highlights that “statistical thinking” should not be confined to a specific function of an organization. It is applicable across the whole spectrum of business activity. The second concept brings out that variation is present in
38、 almost everything. Its existence provides opportunities for better process control and for process performance improvement. The third and fourth concepts stress the need to clearly distinguish between the variation due to “special causes” and that due to “common causes”. The reason for this is that
39、 they give rise to two quite different types of action. A special cause is a sporadic source of variation that demands specific action to restore the status quo. A common cause, on the other hand, is an endemic source of variation that is always present, as it is inherent to the process. A reduction
40、 demands fundamental changes to the process. The elimination of special causes brings a process back under control. The process performance or capability is then stable and predictable. A stable process might, or might not, provide the desired performance. A reduction in common cause variation impro
41、ves process capability or performance. A control chart is the tool used to differentiate between “special causes” and “common causes”. Hence the control chart is a key operational tool in the application of “statistical thinking”. Figure 1 Different classes of data discrete (attribute) (qualitative)
42、 See BS 5702 continuous (measured) (quantitative) Type of data classified into categories (e.g. good/bad) count of events (e.g. nonconformities) constant sample size variable sample size constant sample size variable sample sizeBS 5701-1:2003 4 BSI 31 October 2003 By its very name, a primary role of
43、 a control chart, in an operational sense, is to control; namely to inhibit change. The removal of adverse special cause variation to bring a process back into control does not actually improve the process: it only returns it to its original state. It should be borne in mind, too, that a special cau
44、se can be adverse or beneficial. Suppose a supervisor stands in momentarily for an operator in a process and a special cause is indicated on a fault chart. The special cause could be a single reading above the upper control limit indicating an adverse change. Alternatively, it could be a single read
45、ing below the lower control limit indicating a beneficial change. The reaction to the two types of special causes would be quite different. This focus on control, however, should not blind one to the fact that often the objective, in an overall sense, is to improve process performance by inducing ch
46、ange. Such betterment, through common cause reduction does not necessarily have to await special cause removal. However, the prior removal of special causes gives rise to a stable process and so permits a quantitative prediction of process capability. The generic control and improvement sequence is
47、shown in Figure 2. A significant improvement in process performance is evidenced in a control chart by an “out of control” situation, as is a significant deterioration. Hence the control chart has an in-built statistical test of significance for both improvement and deterioration. Figure 2 Process c
48、ontrol, capability estimation and improvement sequence yes no yes yes no no Select quality characteristic Set-up and run appropriate control chart Is process stable? Estimate process capability Seek reason for special cause Priority for improvement? Reduce common causes Eliminate special cause Is sp
49、ecial cause adverse?BS 5701-1:2003 BSI 31 October 2003 5 4.3.2 Over-control, under-control and control of processes A process monitoring system can give rise to: a) over-control: action is taken when it should not be; b) under-control: action is not taken when it should be; c) control: action is taken when it should be and not taken when it should not be. A process is said to be under a state of (statistical) control when no sp
