Professional Documents
Culture Documents
2007-06-05 (Rev 4)
From
Action
Dead line
Page 2
Ad Hoc Group 1
Application ISO/IEC 17025
Introduction
To meet the technical requirements of the ISO/IEC 17025:2005 under Clause 5, testing
and calibration laboratories need to understand and adopt several statistical methods.
The ISO TC 69 (Applications of Statistical Methods) has over the years developed a
wealth of statistical standards which are relevant and applicable to this situation.
This document gives guidance on the selection and an overview of the referenced
International Standards, Guides, Technical Reports and DIS developed by ISO/TC 69,
other ISO Technical Committees and international organizations on statistical methods.
It is presented from the user perspective in the form of a table, comparing the relevant
ISO/IEC 17025 sub-clauses against these standard documents. DIS are drafts which
can be amended but all documents are available to the public.
The list of ISO statistical International Standards and other relevant documents cited in
this document is neither complete nor exhaustive, and does not preclude the use of any
other ISO standards which are deemed to be of help. Furthermore, this document does
not attempt to prescribe which statistical technique(s) are to be implemented.
A roadmap prepared by the TC69 on the ISO statistical standards is given in Annex A
(Informative). This will provide a quick glance at the statiscal standards available.
A short abstract of each ISO document produced by ISO TC 69 and the other Technical
Committees is appended in Annex B (Informative).
Page 3
5.10.4.2
Compliance
with a
specification
Page 10
Annex A
(Informative)
The cause-and-effect diagram shown below indicates the use of various ISO statistical
standards to arrive at a certain purpose. Although the roadmap does not claim itself to
be complete or exhaustive, it does serve a good purpose for those who wish to have a
quick reference to their needs. It does not preclude the use of any other ISO standards
which are deemed to be of help.
Page 11
ISO Statistical
. standards ATTRIBUTES
ISO 2859-1
VARIABLES
ISO 3951-1
ISO 3951-2
(Click on one standard to find the corresponding abstract) ISO 2859-2 ISO 3951-5
PREDICTION MEAN
. ISO 2859-3
ISO 2859-4
ISO 2859-5
ISO 8423
Bulk material
MEDIAN DIFFERENCE
INTERVAL OF 2 MEANS ISO FDIS 2859-10 ISO 10725
ISO 2854 VARIANCES MEANS ISO FDIS 8422 ISO 11648-1
ISO 16269-7 ISO 2602
ISO 16269-8 ISO 2854 ISO 14560 ISO 11648-2
ISO 2854 ISO 2854
ISO 3301 APP Approach
ISO 13448-1
GUIDE ISO 13448-2
ISO TR 8550-1
ISO TR 8550-2
TOLERANCE NORMAL DESIGN OF
INTERVAL DISTRIBUTION PROPORTIONS POWER OF EXPERIMENTS ISO TR 8550-3 Accept-zero
VARIANCE PROPORTION TESTS ISO 21247
ISO 16269-6 ISO 5479 ISO 11453 ISO 18414
ISO 11453 ISO 3301 ISO 3534-3
Sampling
ISO 2854
ISO 3494 PROCESS
PERFORMANCE
ISO 21747
ISO DTR 12783
TERMINOLOGY
Describe Explain Accept
Statistics Design of experiments Compare
ISO FDIS 3534-1 ISO 3534-3
ISO FDIS 3534-2
Applied statistics
Metrology
VIM
ISO DIS 3534-2 MAKE
ISO 5725-1
ISO 11843-1
A
Follow in ACCURACY
Measurement
DECISION
Metrology
MAINTAINABILITY ADJUSTMENT the time ISO 5725-1 control
VIM
CEI 60706-6-9 CEI 60605-6 ISO 5725-2 GUM
CEI 61649
ISO 5725-3
Reliability
ISO 5725-4 CAPABILITY OF DETECTION
ESTIMATION SAMPLING PLANS
ISO 5725-5 ISO 11843-1
CEI 61073 CEI 60410 CEI 61123 ISO 11843-2 REFERENCE
CEI 60605-4 CEI 61070 LABORATORIES ISO 11843-3 MATERIALS
CAPABILITIES ISO 11843-4
ISO 11095
ISO/CEI Guide 43 ISO Guide 33
ISO 13528 ISO Guide 35
CONTROL CHARTS PROCESS
SPC
ISO DIS 7870-1 CAPABILITY
ISO 21747 UNCERTAINTY OF SPECIFICATION
ISO 11462-1 ISO 7870 ISO 8258
DTR 12783 MEASUREMENT LIMITS
ISO 7966 ISO7873
ISO TR 7871
ISO 13005 (GUM) ISO 10576-1
..\..\abstracts\ISO
ISO TS 21748
7873.doc
Evolution ISO TS 21749
Page 1
Annex B
(Informative)
This International Standard follows on from ISO 2854 and puts forward notions of
the type II risk, the probability of not rejecting the null hypothesis when it is false.
Deals with comparison of a mean with a given value (variance known or unknown),
of two means (variance known or unknown), of a variance with a given value, and of
two variances, and gives sets of curves for these type II risk for a given alternative
and given size of sample and to determine the size of sample to be selected for a
given alternative and a given values of type II risk.
(5) ISO 5479:1997, Guide to statistical interpretation of data — Part 7: Tests for
departure from normality.
This International Standard gives guidance on methods and tests for use in deciding
whether or not the hypothesis of a normal distribution should be rejected, assuming
that the observations are independent. Tests for departure from the normal
distribution are very ineffective for samples of size less than eight.
Three different types of population are considered, namely normally distributed with
unknown standard deviation, normally distributed with known standard deviation,
and continuous but of unknown form. For each of these three types of population,
two methods are presented, one for one-sided prediction intervals and one for
symmetric two-sided prediction intervals. In all cases, there is a choice from among
six confidence levels.
Page 3
(10) ISO 16269, Statistical interpretation of data (The following parts are in
preparation):
Part 3: Tests for departure from normality {and below}
Part 4: Detection and treatment of outliers.
Part 5: Estimation and tests for means and variances for the normal distribution,
with power functions for tests.
(12) ISO 2859-1: 1999 Sampling procedures for inspection by attributes — Part
1: Specification for sampling plans indexed by acceptable quality level (AQL)
for lot-by-lot inspection.
This standard can be used when the switching rules in ISO 2859-1 are not applied.
Indexing is by a preferred series of limiting qualities with a consumer’s risk usually
below 10 % and always below 13 %. Procedures are provided to cater for two
situations: Procedure A to be used when the supplier and the consumer both wish
to regard the lot in isolation (shall be used unless there is a specific instruction to
use Procedure B), Procedure B to be used when the supplier regards the lot as one
of a continuing series but the consumer considers the lot received in isolation.
The skip-lot sampling procedures specified in this standard are applicable to, but
not limited to, inspection of end items, such as complete products or sub-
assemblies, components and raw materials, and materials in process.
This standard establishes the sampling plans and the procedures that can be used
to assess whether the quality level of an entity (lot, process, etc) conforms to a
declared value. The sampling plans have been devised so as o obtain a risk of less
than 5% of contradicting a correct declared quality level. The risk is 10 % of failing
to contradict an incorrect declared quality level that is related to the limiting quality
ratio. Sampling plans are provided corresponding to three levels of discriminatory
ability.
In contrast to the procedures in the other parts of ISO 2859, the procedures in this
standard are not applicable to acceptance assessment of lots. Generally, the
balancing of risks of reaching incorrect conclusions in assessment procedures will
differ from the balancing in the procedures for acceptance sampling.
This standard may be used for various forms of quality inspection in situations
where objective evidence of conformity to some declared quality level is to be
provided by means of inspection of a sample. The procedures are applicable to
entities such as lots, process output, etc that allow random samples of individual
items to be taken from the entity.
This standard specifies an acceptance sampling system of single sampling plans for
inspection by variables, in which the acceptability of a lot is implicitly determined
from an estimate of the percentage of nonconforming items in the process, based
on a random sample of items from the lot. It is primarily designed for application
under the following conditions:
The specified plans apply to end items, components and raw materials, operations,
materials in process, supplies in storage, maintenance operations, data or records,
administrative procedures. Annexes A, B and C form an integral part of this
standard.
This International Standard applies if all the following conditions are satisfied:
This standard establishes the general principles for the application and statistical
treatment of the sampling of bulk materials. It also provides general guidance and
examples for estimating necessary variances and checking precision and bias when
the average value of a quality characteristic is investigated. Furthermore, it also
gives information relating to the statistical analyses of serial data, by the use of
variograms and correlograms.
This standard establishes the basic methods for sampling particulate materials
in bulk (e.g. ores, mineral concentrates, coal, industrial chemicals in powder or
granular form, and agricultural products such as grains) from moving stream and
stationary situations, including stopped-belt sampling, to provide samples for
measuring one or more variables in an unbiased manner and with a known degree
of precision.
It is concerned with the methods of sampling particulate materials in bulk with the
objective of obtaining unbiased measurements of one or more variables of the
material with a known degree of precision. It does not, however, provide methods
for deciding whether to accept or reject a bulk material lot with specified degree of
risk of accepting a sub-standard lot, or of rejecting what is in fact an acceptable lot.
(21) ISO 11648, Statistical aspects of sampling from bulk materials (The
following parts are in preparation):
Part 3: Sampling of liquids.
Part 4: Sampling of gases.
Page 6
This ISO series describes the selection process, general considerations influencing
a selection, making a comparison of the methods for sampling inspection, other
methods sometimes adopted in practice, market and production conditions - effect
on the selection process, the final selection. It is applicable to a wide variety of
inspection situations including end items (e.g. complete products or sub-
assemblies), components and raw materials, services, materials in process,
supplies in storage, maintenance operations, data or records.
c) Control Charts
This International Standard presents key elements and philosophy of the control
chart approach, and identifies a wide variety of control charts, including those
related to the Shewhart control chart, the acceptance control chart and the adaptive
control chart. It presents an overview of the basic principles and concepts and
illustrates the relationships among various control chart approaches to aid in the
selection of the most appropriate standard for given circumstance, It does not
specify statistical control methods using control charts.
This International Standard gives the principles of CUSUM charting and includes
guidance on the preparation and interpretation of CUSUM charts using basic
decision rules.
(25) ISO 7873:1993, Control charts for arithmetic average with warning limits.
This standard specifies procedures for the statistical control of processes by using
control charts based on calculating the arithmetic average of a sample and using
warning limits and action limits. It is assumed that for large lots and for the mass
output of piece and batch production, such a measure of quality is a random
variable following a normal distribution. However, when averages of four or more
items are plotted, this assumption of a normal distribution is not necessary for
control purposes.
This International Standard gives guidance on the uses of acceptance control charts
and establishes general procedures for determining sample sizes, action limits and
decision criteria. Examples are included to illustrate a variety of circumstances in
which this technique has advantages and to provide details of the determination of
the sample size, the action limits and the decision criteria.
This International Standard establishes a guide to the use and understanding of the
control chart approach to the methods for statistical control of a process.
Page 7
This International Standard defines 204 probability and general statistical terms in
English and French which may be used in the drafting of other international
standards. The terms are classified under the following main headings:
This standard defines applied statistics terms, and expresses them in a conceptual
framework in accordance with ISO normative terminology practice. Term entries are
arranged thematically. An alphabetical index is provided. Standardized symbols and
abbreviations are defined.
Its two principal purposes are, specifically, to establish a common vocabulary for
use throughout ISO/TC 69 standards, together with the broader intent to enhance
the preciseness, clarity and cohesiveness in the usage/application of applied
statistics generally. The mathematical level has deliberately been kept to a low level
in order for the content to be made readily comprehensible to the widest possible
readership.
This standard defines the terms used in the field of design of experiments and may
be used in the drafting of other International Standards.
e) Accuracy
This standard provides basic methods for estimating the bias of a measurement
method and the laboratory bias when a measurement method is applied. In order
that the measurements are made in the same way, it is important that the
measurement method has been standardized. It can be applied only if the accepted
reference value can be established a s a conventional true value, e.g. by
measurement standards or suitable reference materials or by referring to a
reference measurement method or by preparation of a known sample.
Part 5 of ISO 5725 describes two experiments that may be used in circumstances
where the experiment described in Part 2 would give biased estimates of
repeatability and reproducibility standard deviations. One is appropriate when there is
a risk that operators may allow the result of a measurement on one sample to
influence the result of a subsequent measurement on another sample of the same
material. The other is appropriate when the materials to be used in the experiment
are such that one cannot be confident that identical samples can be prepared. Part 5
also describes "robust" methods of analysing the data obtained from the experiments
described in Part 2 and 5..
Page 9
The purpose is to give some indications of the way in which accuracy data can be
used in various practical situations by:
(39) ISO Guide 30:1992, Terms and definitions used in connection with
reference materials
This Guide recommends the terms and their meaning used in connection
with reference materials, taking into account those terms which are used
in reference material certificates and appropriate test reports.
(40) ISO Guide 32:1997, Calibration in analytical chemistry and use of certified
reference materials
h) Capability of detection
Part 2 of this International Standard sets out the design of experiments that may be
used to estimate the terms defined in Part 1, and describes how to calculate
estimates of their values from the experimental data. In the section on the reporting
and use of results in contains the important requirement that results that fall below
the critical value of the net state variable should not be reported as “zero” or
“smaller than minimum detectable value” – in such cases the actual value should
always be reported.
This standard gives a method of estimating the critical value of the response
variable from the mean and standard deviation of repeated measurements of the
reference state in certain situations in which the value of the net state variable is
zero, for all reasonable and foreseeable purposes. Hence, it can be decided
whether values of the response variable in an actual state (or test sample) are
above the range of values attributable to the reference state.
The procedure given in this part of ISO 11843 is recommended for situations in
which it is difficult to obtain a large amount of the actual states although a large
amount of the basic state can be prepared.
Page 11
i) Measurement uncertainty
This Technical Specification follows the approach taken in the GUM and establishes
the basic structure for stating and combining components of uncertainty. To this
basic structure, it adds a statistical framework using the analysis of variance
(ANOVA) for estimating individual components, particularly those obtained by Type
A evaluation of uncertainty, i.e. based on the use of statistical methods. A short
description of Type B evaluation of uncertainty (non-statistical) is included for
completeness.
The Guide establishes general rules for evaluating and expressing uncertainty in
measurement that can be followed at various levels of accuracy and in many fields
– from the shop floor to fundamental research. Therefore, the principles of the
Guide are intended to be applicable to a broad spectrum of measurements,
Page 12
including those required for: maintaining quality control and quality assurance in
production; complying with and enforcing laws and regulations; conducting basic
research, and applied research and development in science and engineering;
calibrating standards and instruments and performing tests throughout a national
measurement system in order to achieve traceability to national standards;
developing, maintaining, and comparing international and national physical
reference standards, including reference materials. The Guide is primarily
concerned with the expression of uncertainty in the measurement of a well-defined
physical quantity – the measurand – that can be characterized by an essentially
unique value. It is also applicable to evaluating and expressing uncertainty
associated with the conceptual design and theoretical analysis of experiments,
methods of measurement and complex components and systems. The Guide
provides general rules for evaluating and expressing uncertainty in measurement
rather than detailed, technology-specified instructions. Both short and more detailed
examples are included.
This Technical Report provides users with practical guidance to the use of ISO
5725-2:1994 and presents simplified step-by-step approaches for the design,
implementation, and statistical analysis of inter-laboratory studies for assessing the
variability of a standard measurement method and in the determination of
repeatability and reproducibility of data obtained in inter-laboratory testing.
k) Conformity of specifications
ISO 10576-1:2002 sets out guidelines for drafting requirements that may be
formulated as limiting values for a quantifiable characteristic and for checking
conformity to such requirements when the test or measurement result is subject to
uncertainty.
It is outside the scope of ISO 10576-1:2002 to give rules for how to act when an
inconclusive result of a conformity test has been obtained.
Statistical process control (SPC) concerns the use of statistical techniques and/or
statistical or stochastic control algorithms to achieve one or more of the following
objectives:
a) to increase knowledge about a process;
b) to steer a process to behave in the desired way;
c) to reduce variation of final-product parameters, or in other ways improve
performance of a process.
These guidelines give the elements for implementing an SPC system to achieve
these objectives.
This Technical Report gives guidance on the selection and an overview of all the
referenced International Standards, Guides, Technical Reports and DIS developed
by ISO/TC 69 from a user perspective. DIS are drafts which can be amended. All
these documents are available to the public. This TR also gives two descriptions of
the content of the International Standards by two sets of abstracts: non-technical
abstracts and technical abstracts of all these documents. Each abstract presents a
brief survey of the content of the actual standard or DIS. It also gives indications of
the use of the document in different areas.
Page 14
This International Standard specifies a system of single sampling schemes for lot-
by-lot inspection by attributes. All the sampling plans of the system are of accept-
zero form, i.e. no lot is accepted if the sample from it contains one or more
nonconforming items. The schemes depend on a suitably-defined average outgoing
quality limit (AOQL), the value of which is chosen by the user; no restrictions are
placed on the choice of the value of the AOQL or on the sizes of successive lots in
the series. The methodology ensures that the overall average quality reaching the
customer or market-place will not exceed the AOQL in the long run.
It is designed for use under the following conditions: 1) where the inspection
procedure is to be applied to a series of lots of discrete items that are intended to
be identical, and which are all supplied by one producer using one production
process; 2) where one or more quality characteristics of these products are taken
into consideration, which must all be classifiable as either conforming or
nonconforming; 3) where the inspection error involved in classifying the state of a
product's quality characteristic(s) is negligible; and 4) where inspection is non-
destructive.