1、 Collection of SANS standards in electronic format (PDF) 1. Copyright This standard is available to staff members of companies that have subscribed to the complete collection of SANS standards in accordance with a formal copyright agreement. This document may reside on a CENTRAL FILE SERVER or INTRA
2、NET SYSTEM only. Unless specific permission has been granted, this document MAY NOT be sent or given to staff members from other companies or organizations. Doing so would constitute a VIOLATION of SABS copyright rules. 2. Indemnity The South African Bureau of Standards accepts no liability for any
3、damage whatsoever than may result from the use of this material or the information contain therein, irrespective of the cause and quantum thereof. ISBN 978-0-626-23197-2 SANS 5725-6:2009Edition 1 and ISO tech. corr. 1ISO 5725-6:1994Edition 1 and tech. corr. 1SOUTH AFRICAN NATIONAL STANDARD Accuracy
4、(trueness and precision) of measurement methods and results Part 6: Use in practice of accuracy values This national standard is the identical implementation of ISO 5725-6:1994 and ISO technical corrigendum 1, and is adopted with the permission of the International Organization for Standardization.
5、Published by SABS Standards Division 1 Dr Lategan Road Groenkloof Private Bag X191 Pretoria 0001Tel: +27 12 428 7911 Fax: +27 12 344 1568 www.sabs.co.za SABS SANS 5725-6:2009 Edition 1 and ISO tech. corr. 1 ISO 5725-6:1994 Edition 1 and tech. corr. 1 Table of changes Change No. Date Scope ISO tech.
6、corr. 1 2001 Corrected to replace table 14 and subclause 8.4.9.2 a). National foreword This South African standard was approved by National Committee SABS TC 169, Applications of statistical methods, in accordance with procedures of the SABS Standards Division, in compliance with annex 3 of the WTO/
7、TBT agreement. This SANS document was published in October 2009. ICS 03.120.30 Ref. No. ISO 5725-6:1994/Cor.1:2001(E) ISO 2001 All rights reserved Printed in Switzerland INTERNATIONAL STANDARD ISO 5725-6:1994 TECHNICAL CORRIGENDUM 1 Published 2001-10-15 INTERNATIONAL ORGANIZATION FOR STANDARDIZATION
8、 ORGANISATION INTERNATIONALE DE NORMALISATIONAccuracy (trueness and precision) of measurement methods and results Part 6: Use in practice of accuracy values TECHNICAL CORRIGENDUM 1 Exactitude (justesse et fidlit) des rsultats et mthodes de mesure Partie 6: Utilisation dans la pratique des valeurs de
9、xactitude RECTIFICATIF TECHNIQUE 1 Technical Corrigendum 1 to International Standard ISO 5725-6:1994 was prepared by Technical Committee ISO/TC 69, Applications of statistical methods, Subcommittee SC 6, Measurement methods and results. Page 35, Table 14 Replace Table 14 with the following table: SA
10、NS 5725-6:2009This s tandard may only be used and printed by approved subscription and freemailing clients of the SABS .ISO 5725-6:1994/Cor.1:2001(E) 2 ISO 2001 All rights reservedTable 14 Values of (A, B, , ) or (A, B, , ) for = 0,05 and = 0,05 AB6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 25 50 200 6
11、 4,99 4,64 4,39 4,21 4,07 3,95 3,86 3,79 3,72 3,67 3,62 3,58 3,54 3,51 3,48 3,37 3,17 3,02 7 4,69 4,35 4,11 3,93 3,79 3,68 3,59 3,52 3,45 3,40 3,35 3,31 3,28 3,25 3,22 3,11 2,91 2,77 8 4,48 4,14 3,90 3,73 3,59 3,48 3,40 3,32 3,26 3,21 3,16 3,12 3,09 3,06 3,03 2,93 2,72 2,58 9 4,32 3,99 3,75 3,58 3,4
12、4 3,34 3,25 3,18 3,12 3,06 3,02 2,98 2,94 2,91 2,89 2,78 2,58 2,44 10 4,19 3,86 3,63 3,46 3,33 3,22 3,13 3,06 3,00 2,95 2,91 2,87 2,83 2,80 2,77 2,67 2,47 2,33 11 4,09 3,77 3,54 3,37 3,23 3,13 3,04 2,97 2,91 2,86 2,81 2,78 2,74 2,71 2,68 2,58 2,38 2,24 12 4,01 3,69 3,46 3,29 3,16 3,05 2,97 2,90 2,84
13、 2,78 2,74 2,70 2,67 2,64 2,61 2,51 2,31 2,16 13 3,94 3,62 3,39 3,22 3,09 2,99 2,90 2,83 2,77 2,72 2,68 2,64 2,60 2,57 2,55 2,44 2,24 2,10 14 3,88 3,56 3,34 3,17 3,04 2,94 2,85 2,78 2,72 2,67 2,62 2,59 2,55 2,52 2,49 2,39 2,19 2,04 15 3,83 3,52 3,29 3,12 2,99 2,89 2,80 2,73 2,67 2,62 2,58 2,54 2,51
14、2,47 2,45 2,34 2,14 1,99 16 3,79 3,47 3,25 3,08 2,95 2,85 2,76 2,69 2,63 2,58 2,54 2,50 2,47 2,43 2,41 2,30 2,10 1,95 17 3,75 3,44 3,21 3,05 2,92 2,81 2,73 2,66 2,60 2,55 2,50 2,46 2,43 2,40 2,37 2,27 2,07 1,92 18 3,72 3,41 3,18 3,02 2,89 2,78 2,70 2,63 2,57 2,52 2,47 2,43 2,40 2,37 2,34 2,24 2,03 1
15、,88 19 3,69 3,38 3,15 2,99 2,86 2,75 2,67 2,60 2,54 2,49 2,44 2,41 2,37 2,34 2,31 2,21 2,01 1,85 20 3,67 3,35 3,13 2,96 2,83 2,73 2,65 2,58 2,52 2,46 2,42 2,38 2,35 2,32 2,29 2,18 1,98 1,83 25 3,57 3,25 3,03 2,87 2,74 2,64 2,55 2,48 2,42 2,37 2,33 2,29 2,25 2,22 2,19 2,09 1,88 1,72 50 3,37 3,07 2,85
16、 2,68 2,55 2,45 2,37 2,30 2,24 2,18 2,14 2,10 2,06 2,03 2,00 1,89 1,67 1,50 200 3,24 2,93 2,71 2,55 2,42 2,32 2,23 2,16 2,10 2,04 2,00 1,96 1,92 1,89 1,86 1,75 1,51 1,29 NOTES 1 BArr= ; ( )AAA1pn =; ( )BBB1pn = 2 22BLB B22ALA Arrnn+= +; AA1p =; BB1p = SANS 5725-6:2009This s tandard may only be used
17、and printed by approved subscription and freemailing clients of the SABS .ISO 5725-6:1994/Cor.1:2001(E) ISO 2001 All rights reserved 3Page 37, subclause 8.4.9.2.2 a) Replace 8.4.9.2.2 a) with the following: 8.4.9.2.2 Both methods are new candidate standard methods a) Within-laboratory precision 2B2A
18、rrrsFs= If ( )()( )/2 BA BA1/2,rr r rrFFF uu there is no evidence that the methods have different within-laboratory precisions; if ( )/2 B A,rrrFF there is evidence that method B has poorer within-laboratory precision than method A. ( )/2 B A,rrF and ()( )BA1/2,rrFare the /2- and (1/2)-quantiles of
19、the F distribution with degrees of freedom of numerator rBand denominator rA( )BBB1rpn = ( )AAA1rpn = SANS 5725-6:2009This s tandard may only be used and printed by approved subscription and freemailing clients of the SABS .INTERNATIONAL STANDARD 57 5-6 First edition 1994-l 2-l 5 Accuracy (trueness
20、and precision) of measurement methods and results - Part 6: Use in practice of accuracy values Exactitude (justesse et fid the factors that influence the outcome of a measurement cannot all be completely controlled. In the practical interpretation of measurement data, this vari- ability has to be ta
21、ken into account. For instance, the difference between a test result and some specified value may be within the scope of una- voidable random errors, in which case a real deviation from such a speci- fied value has not been established. Similarly, comparing test results from two batches of material
22、will not indicate a fundamental quality difference if the difference between them can be attributed to the inherent variation in the measurement procedure. 0.3 Parts 1 to 5 of IS0 5725 dicuss the background to, and given methods for, the assessment of the precision (in terms of the repeatability sta
23、ndard deviation and the reproducibility standard deviation) and the trueness (in terms of the various components of bias) of measurements produced by a standard measurement method. Such assessment would, however, be pointless if there were no practical uses to which the results could be put. 0.4 Giv
24、en that the accuracy of a measurement method has been estab- lished, this part of IS0 5725 applies that knowledge in practical situations in such a way as to facilitate commercial transactions and to monitor and improve the operational performance of laboratories. SANS 5725-6:2009This s tandard may
25、only be used and printed by approved subscription and freemailing clients of the SABS .This page intentionally left blank SANS 5725-6:2009This s tandard may only be used and printed by approved subscription and freemailing clients of the SABS .INTERNATIONAL STANDARD 0 IS0 IS0 5725-6: 1994(E) Accurac
26、y (trueness and precision) of measurement methods and results - Part 6: Use in practice of accuracy values 1 Scope 1.1 The purpose of this part of IS0 5725 is to give some indications of the way in which accuracy data can be used in various practical situations by: a) giving a standard method of cal
27、culating the re- peatability limit, the reproducibility limit and other limits to be used in examining the test results obtained by a standard measurement method; b) providing a way of checking the acceptability of test results obtained under repeatability or repro- ducibility conditions; describing
28、 how to assess the stability of results within a laboratory over a period of time, and thus providing a method of “quality control” of the op- erations within that laboratory; describing how to assess whether a given labora- tory is able to use a given standard measurement method in a satisfactory w
29、ay; e) describing how to compare alternative measure- ment methods. 1.2 This part of IS0 5725 is concerned exclusively with measurement methods which yield measure- ments on a continuous scale and give a single nu- merical figure as the result, although this single figure may be the outcome of a cal
30、culation from a set of observations. 1.3 It is assumed that the estimates of trueness and precision for the method have been obtained in accordance with parts 1 to 5 of IS0 5725. 1.4 Any additional information regarding the field of application will be given at the beginning of each par- ticular app
31、lication. 2 Normative references The following standards contain provisions which, through reference in this text, constitute provisions of this part of IS0 5725. At the time of publication, the editions indicated were valid. All standards are subject to revision, and parties to agreements based on
32、this part of IS0 5725 are encouraged to investigate the possibility of applying the most recent editions of the standards indicated below. Members of IEC and IS0 maintain registers of currently valid International Standards. 1 SANS 5725-6:2009This s tandard may only be used and printed by approved s
33、ubscription and freemailing clients of the SABS .IS0 5725-6: 1994(E) 0 IS0 IS0 3534-l : 1993, bols - Part 1: terms. IS0 5725-l : 1994, Accuracy (trueness and precision) of measurement methods and results - Part 1: General principles and definitions. IS0 5725-2: 1994, Accuracy (trueness and precision
34、) Statistics - Vocabulary and sym- Probability and general statistical of measurement methods and results - Part 2: Basic method for the determination of repeatability and re- producibility of a standard measurement method. IS0 5725-3: 1994, Accuracy (trueness and precision) of measurement methods a
35、nd results - Part 3: Intermediate measures of the precision of a standard measurement method. IS0 5725-4: 1994, Accuracy (trueness and precision) of measurement methods and results - Part 4: Basic methods for the determination of the trueness of a standard measurement method. IS0 8258:1991, Shewhart
36、 control charts. IS0 Guide 33:1989, Uses of certified reference ma- terials. IS0 Guide 35:1989, Certification of reference ma- terials - General and statistical principles. lSO/l EC Guide 25: 1990, General requirements for the competence of calibration and testing labora- tories. 3 Definitions For t
37、he purposes of this part of IS0 5725, the defi- nitions given in IS0 3534-l and IS0 5725-l apply. The symbols used in IS0 5725 are given in annex A. 4 Determination of limits 4.1 Repeatability and reproducibility limits 4.1.1 In IS0 5725-2, attention has been focussed on estimating the standard devi
38、ations associated with operations under repeatability or reproducibility condi- tions. However, normal laboratory practice requires examination of the difference(s) observed between two (or more) test results, and for this purpose some measure akin to a critical difference is required, rather than a
39、 standard deviation. 4.1.2 When a quantity is based on sums or differ- ences of II independent estimates each having a standard deviation 0, then that resultant quantity will have a standard deviation 0 lr yt . The reproducibility limit (R) or repeatability limit (r) are for differences between two
40、test results, so the associated standard deviation is 0 I/- 2 . In normal statistical practice, for examining the difference between these two values the critical difference used is f times this standard deviation, i.e. fa Jr 2 . The value off (the critical range factor) depends on the probability l
41、evel to be associ- ated with the critical difference and on the shape of the underlying distribution. For the reproducibility and repeatability limits, the probability level is specified as 95 %, and throughout the analysis in IS0 5725 the assumption is made that the underlying distribution is appro
42、ximately normal. For a normal distribution at 95 % probability level, f is I,96 and ffi then is 2,77. As the purpose of this part of IS0 5725 is to give some simple “rule of thumb” to be applied by non- statisticians when examining the results of tests, it seems reasonable to use a rounded value of
43、2,8 in- stead of ffi. 4.1.3 As has been stated, the process of estimating precision leads to estimates of the true standard de- viations while the true standard deviations remain unknown. Therefore in statistical practice they should be denoted by s rather than 0. However, if the pro- cedures given
44、in IS0 5725-l and IS0 5725-2 are fol- lowed, these estimates will be based on an appreciable number of test results, and will give the best information we are likely to have of the true val- ues of the standard deviations. In other applications that follow, for estimates of these standard deviations
45、 based on more limited data, the symbol s (estimate of a standard deviation) is used. Therefore it seems best to use the symbol 0 to denote the values ob- tained from a full precision experiment, and treat these as true standard deviations with which other estimates (s) will be compared. 4.1.4 In vi
46、ew of 4.1 .I to 4.1.3, when examining two single test results obtained under repeatability or re- producibility conditions, the comparison shall be made with the repeatability limit r = 2,8a, or the reproducibility limit R = 2,8a, SANS 5725-6:2009This s tandard may only be used and printed by approv
47、ed subscription and freemailing clients of the SABS .0 IS0 IS0 5725-6: 1994(E) 4.2 Comparisons based on more than two values 4.2.1 Two groups of measurements in one laboratory If, in one laboratory under repeatability conditions, two groups of measurements are performed with the first group of ytl t
48、est results giving an arithmetic mean of 7, and the second group of % test results giving an arithmetic mean of y2, then the standard deviation of (7, - 5) is and the critical difference for 17, - yzi is CD=2,8a, -+ J 1 2% NOTE 2 If n1 and n2 are both unity, this reduces to R = 2,8, as expected. 4.2
49、.3 Comparison with a reference value for one laboratory If 1 test results are obtained under repeatability con- ditions within one laboratory which give an arithmetic mean of 7, then the comparison with a given refer- ence value p. shall be made, in the absence of spe- cific knowledge of the laboratory component of bias, using a standard deviation for (7 - po) of CJ = lr 0: + ; o* r 1 =- J- 2 J 2(0:+0;) -241 -4) 1 at the 95 % probability leve
