1、 g49g50g3g38g50g51g60g44g49g42g3g58g44g55g43g50g56g55g3g37g54g44g3g51g40g53g48g44g54g54g44g50g49g3g40g59g38g40g51g55g3g36g54g3g51g40g53g48g44g55g55g40g39g3g37g60g3g38g50g51g60g53g44g42g43g55g3g47g36g58equivalency of results ICS 13.060.45Water quality Guidance for establishing the DRAFT FOR DEVELOPME
2、NTDD ISO/TS 16489:2006Incorporating Corrigendum No. 1DD ISO/TS 16489:2006This Draft for Development was published under the authority of the Standards Policy and Strategy Committee on 31 July 2006 BSI 2006ISBN 0 580 48955 8comments will be welcomed. These should be sent to the Secretary of BSI Subco
3、mmittee EH/3/2, Physical, chemical and biochemical methods, at British Standards House, 389 Chiswick High Road, London W4 4AL, giving the document reference and clause number and proposing, where possible, an appropriate revision of the text.A list of organizations represented on this subcommittee c
4、an be obtained on request to its secretary.This publication does not purport to include all the necessary provisions of a contract. Users are responsible for its correct application.Amendments issued since publicationAmd. No. Date Comments16787 Corrigendum No. 129 December 2006 Correction to the cal
5、culated result of tcalcin Annex BA review of this Draft for Development will be carried out not later than 2 years after its publication.Notification of the start of the review period, with a request for the submission of comments from users of this Draft for Development, will be made in an announce
6、ment in the appropriate issue of Update Standards. According to the replies received, the responsible BSI Committee will judge whether the Draft for Development can be converted into a British Standard or what other action should be taken.Observations which it is felt should receive attention before
7、 the official call for National forewordThis Draft for Development reproduces verbatim ISO/TS 16489:2006, incorporating Corrigendum November 2006.This publication is not to be regarded as a British Standard.It is being issued in the Draft for Development series of publications and is of a provisiona
8、l nature. It should be applied on this provisional basis, so that information and experience of its practical application can be obtained.Reference numberISO/TS 16489:2006(E)TECHNICAL SPECIFICATION ISO/TS16489First edition2006-05-15Water quality Guidance for establishing the equivalency of results Q
9、ualit de leau Lignes directrices pour la cration de lquivalence des rsultats DD ISO/TS 16489:2006ii iiiContents Page Foreword iv Introduction v 1 Scope 1 2 Normative references 1 3 Terms and definitions .1 4 Overview of the different approaches .2 5 Amount of data.2 6 Data comparisons3 7 Comparison
10、of arithmetic means of two independently obtained sets of data 3 8 Comparison of population and sample arithmetic means 4 9 Analysis of variance 5 10 Determination of the equivalence of analytical results obtained from samples from different matrices.7 10.1 General7 10.2 Determination of the equival
11、ence of the analytical results of real samples using orthogonal regression.7 10.3 Evaluation according to the difference method .9 11 Reporting 10 Annex A (informative) Statistical tables11 Annex B (informative) Example of a comparison of arithmetic means of two independently obtained sets of data.1
12、3 Annex C (informative) Example of a comparison of population and sample arithmetic means.15 Annex D (informative) Example of an analysis of variance 16 Annex E (informative) Examples of a comparison of results from samples of different matrices.18 Annex F (informative) Illustrative examples of grap
13、hic plots.24 Annex G (informative) Schematic diagrams27 Bibliography 29 DD ISO/TS 16489:2006iv Foreword ISO (the International Organization for Standardization) is a worldwide federation of national standards bodies (ISO member bodies). The work of preparing International Standards is normally carri
14、ed out through ISO technical committees. Each member body interested in a subject for which a technical committee has been established has the right to be represented on that committee. International organizations, governmental and non-governmental, in liaison with ISO, also take part in the work. I
15、SO collaborates closely with the International Electrotechnical Commission (IEC) on all matters of electrotechnical standardization. International Standards are drafted in accordance with the rules given in the ISO/IEC Directives, Part 2. The main task of technical committees is to prepare Internati
16、onal Standards. Draft International Standards adopted by the technical committees are circulated to the member bodies for voting. Publication as an International Standard requires approval by at least 75 % of the member bodies casting a vote. In other circumstances, particularly when there is an urg
17、ent market requirement for such documents, a technical committee may decide to publish other types of normative document: an ISO Publicly Available Specification (ISO/PAS) represents an agreement between technical experts in an ISO working group and is accepted for publication if it is approved by m
18、ore than 50 % of the members of the parent committee casting a vote; an ISO Technical Specification (ISO/TS) represents an agreement between the members of a technical committee and is accepted for publication if it is approved by 2/3 of the members of the committee casting a vote. An ISO/PAS or ISO
19、/TS is reviewed after three years in order to decide whether it will be confirmed for a further three years, revised to become an International Standard, or withdrawn. If the ISO/PAS or ISO/TS is confirmed, it is reviewed again after a further three years, at which time it must either be transformed
20、 into an International Standard or be withdrawn. Attention is drawn to the possibility that some of the elements of this document may be the subject of patent rights. ISO shall not be held responsible for identifying any or all such patent rights. ISO/TS 16489 was prepared by Technical Committee ISO
21、/TC 147, Water quality, Subcommittee SC 2, Physical, chemical and biochemical methods. DD ISO/TS 16489:2006vIntroduction The methods referred to in this Technical Specification can comprise a standard or reference method, the results of which are to be compared with results generated by an alternati
22、ve, perhaps more simple, method. Alternatively, a comparison of results produced by an old established method and those produced by a new more modern technique can be undertaken. The methods can be laboratory based or undertaken “on-site” where the samples are taken. No indication is given to confir
23、m whether either one of the two methods, in terms of bias, is better or worse than the other method, only that the results produced by both methods are considered equivalent or not, in terms of the calculated means, standard deviations and variances. The procedures described are not to be used for,
24、and do not apply to, situations to establish whether two methods can be shown to be equivalent. The procedures apply only to demonstrating equivalency of results. Since standard deviations and means can vary with concentrations, especially where concentrations vary over several orders of magnitude,
25、the procedures described in Clauses 7 to 9 are only applicable to samples containing a single level of concentration. It would be necessary to repeat the procedures for each concentration level if different concentration levels are encountered, and it is shown that standard deviations and means vary
26、 over these concentration levels. It might be that the demonstration of equivalence can only be achieved over relatively small concentration ranges. For multiple concentration levels, the procedures described in Clause 10 might be applicable. In addition, the laboratory will need to show that both m
27、ethods are suitable and appropriate for the sample matrix and the parameter under investigation, including the level of concentration of the parameter. Also, the experimental data obtained in the comparison of results should reflect the specific application for which equivalence is questioned, as di
28、fferent matrices can lead to different results with the two methods. Throughout this Technical Specification, it is assumed that results are obtained essentially under repeatability conditions, but it is recognized that this will not always be so. Hence, where appropriate, identical samples are anal
29、ysed by the same analyst using the same reagents and equipment in a relatively short period of time. Furthermore, a level of confidence of 95 % is assumed. The statistical tests described in this Technical Specification assume that the data to be compared are independent and normally distributed in
30、a Gaussian manner. If they are not, the data might not be suitable for the statistical treatments described and additional data might need to be collected. The power of the statistical test is greatly enhanced when sufficient data are available for comparisons; i.e. when the numbers of degrees of fr
31、eedom are available to enable a meaningful interpretation to be made. However, it is recognized that a statistically significant difference might not necessarily infer an important or meaningful difference, and a personal judgement should be made on whether a statistically significant difference is
32、important or meaningful and relevant. Alternatively, a statistical test might not be sufficiently powerful to be able to detect a difference that from a practical point of view could be regarded as important or meaningful. To aid the analyst, advice is provided as to which clause (and corresponding
33、annex) is applicable to the circumstances surrounding the data that have been generated. It is recognized that when results are compared they can have been generated under a variety of different conditions. DD ISO/TS 16489:2006blank1Water quality Guidance for establishing the equivalency of results
34、1 Scope This Technical Specification describes statistical procedures to test the equivalency of results obtained by two different analytical methods used in the analysis of waters. This Technical Specification is not applicable for establishing whether two methods can be shown to be equivalent. The
35、 procedures given in this Technical Specification are only applicable to demonstrating the equivalency of results. 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 refer
36、ences, the latest edition of the referenced document (including any amendments) applies. ISO 5725-2, Accuracy (trueness and precision) of measurement methods and results Part 2: Basic method for the determination of repeatability and reproducibility of a standard measurement method NOTE A practical
37、guidance document to assist in the use of ISO 5725-2 has been published: see ISO/TR 22971. 3 Terms and definitions For the purposes of this document, the following terms and definitions apply: 3.1 precision closeness of agreement between independent test results obtained under repeatability conditio
38、ns NOTE 1 Precision depends only on the distribution of random errors and does not relate to the true, specified or accepted value. NOTE 2 Measurement of precision is usually expressed in terms of imprecision and computed as a standard deviation of the test results. Less precision is reflected by a
39、larger standard deviation. NOTE 3 “Independent test results” means results obtained in a manner not influenced by any previous result on the same sample. Quantitative measurements of precision depend critically on stipulated conditions. 3.2 repeatability conditions conditions where independent test
40、results are obtained with the same method on identical test samples in the same laboratory, by the same operator, using the same reagents and equipment within short intervals of time 3.3 analytical method unambiguously written procedure describing all details required to carry out the analysis of th
41、e determinand or parameter, namely: scope and field of application, principle and/or reactions, definitions, reagents, apparatus, analytical procedures, calculations and presentation of results, performance data and test report DD ISO/TS 16489:20062 4 Overview of the different approaches Where a sam
42、ple is analysed in replicate using two methods, then the procedures described in Clause 7 and Annex B may be used. The results should, ideally, be generated by a single analyst, however, it is recognized that different analysts can be involved. The procedures described in Clause 8 and Annex C might
43、be applicable where, over a period of time, samples are analysed by different analysts using a particular method and these results are compared with results generated using an alternative method that is carried out by one or more analysts. In this case, however, the assumption of repeatability will
44、not be applicable. Where different analysts are involved in the generation of data, the procedures described in Clause 9 and Annex D may be used. In these cases, the assumption of repeatability will not be applicable. Where identical samples are analysed by one or more analysts using two different m
45、ethods, the procedures described in Clause 10 and Annex E might be more appropriate. This might be applicable where the same or different concentration levels are indicated. 5 Amount of data The approach described in this Technical Specification demonstrates the importance that the power of the sign
46、ificance tests lies in the amount of data available as well as the quality (spread) of the data. Throughout this Techncial Specification, it is assumed that the level of confidence is established at 95 %. This might represent a degree of acceptability that is insufficient for certain purposes. This
47、would mean that individual circumstances would merit individual consideration as to whether this Technical Specification, in terms of the confidence level used, should be applied. Confidence levels of 99 % or higher might be, in certain circumstances, more appropriate. In addition, where a statistic
48、ally significant difference has been suggested by a statistical analysis of the data, there is always a need to question whether this difference is important or relevant, in terms of its suitability and fitness for purpose, and not in terms of its statistical meaning or understanding. This judgement
49、 should be based on whether the analytical results are fit for their intended purpose. For example, with large amounts of data, it is possible to conclude that there is a statistically significant difference between 50,1 and 50,2. Whether this difference is important or meaningful is another matter when deciding on the suitability of the method. Before any statistical treatment is undertaken, it is always useful to plot a graph of the data. This will provide a visual display of the results, an inspection of which should reveal the amo
