1、Designation: E691 15 An American National StandardStandard Practice forConducting an Interlaboratory Study to Determine thePrecision of a Test Method1This standard is issued under the fixed designation E691; the number immediately following the designation indicates the year oforiginal adoption or,
2、in the case of revision, the year of last revision. A number in parentheses indicates the year of last reapproval. Asuperscript epsilon () indicates an editorial change since the last revision or reapproval.This standard has been approved for use by agencies of the U.S. Department of Defense.1. Scop
3、e1.1 This practice describes the techniques for planning,conducting, analyzing, and treating the results of an interlabo-ratory study (ILS) of a test method. The statistical techniquesdescribed in this practice provide adequate information forformulating the precision statement of a test method.1.2
4、This practice does not concern itself with the develop-ment of test methods but rather with gathering the informationneeded for a test method precision statement after the devel-opment stage has been successfully completed. The dataobtained in the interlaboratory study may indicate, however,that fur
5、ther effort is needed to improve the test method.1.3 Since the primary purpose of this practice is the devel-opment of the information needed for a precision statement, theexperimental design in this practice may not be optimum forevaluating materials, apparatus, or individual laboratories.1.4 Field
6、 of ApplicationThis practice is concerned exclu-sively with test methods which yield a single numerical figureas the test result, although the single figure may be the outcomeof a calculation from a set of measurements.1.4.1 This practice does not cover methods in which themeasurement is a categoriz
7、ation; however, for many practicalpurposes categorical outcomes can be scored, such as zero-onescoring for binary measurements or as integers, ranks forexample, for well-ordered categories and then the test resultcan be defined as an average, or other summary statistic, ofseveral individual scores.1
8、.5 This standard may involve hazardous materials,operations, and equipment. This standard does not purport toaddress all of the safety problems associated with its use. It isthe responsibility of the user of this standard to establishappropriate safety and health practices and determine theapplicabi
9、lity of regulatory limitations prior to use.2. Referenced Documents2.1 ASTM Standards:2E29 Practice for Using Significant Digits in Test Data toDetermine Conformance with SpecificationsE177 Practice for Use of the Terms Precision and Bias inASTM Test MethodsE456 Terminology Relating to Quality and S
10、tatisticsE1169 Practice for Conducting Ruggedness TestsE1402 Guide for Sampling DesignE2282 Guide for Defining the Test Result of a Test Method3. Terminology3.1 DefinitionsTerminology E456 provides a more exten-sive list of terms in E11 standards.3.1.1 accuracy, nthe closeness of agreement between a
11、test result and an accepted reference value. E1773.1.2 bias, nthe difference between the expectation of thetest results and an accepted reference value. E1773.1.3 interlaboratory study, (ILS) in ASTM, na designedprocedure for obtaining a precision statement for a test method,involving multiple labor
12、atories, each generating replicate testresults on one or more materials.3.1.4 observation, nthe process of obtaining informationregarding the presence or absence of an attribute of a testspecimen, or of making a reading on a characteristic ordimension of a test specimen. E22823.1.5 precision, nthe c
13、loseness of agreements betweenindependent test results obtained under stipulated conditions.E1773.1.6 repeatability, nprecision under repeatabilityconditions. E1773.1.7 repeatability conditions, nconditions where inde-pendent test results are obtained with the same method onidentical test items in t
14、he same laboratory by the same operatorusing the same equipment within short intervals of time. E1771This practice is under the jurisdiction ofASTM Committee E11 on Quality andStatistics and is the direct responsibility of Subcommittee E11.20 on Test MethodEvaluation and Quality Control.Current edit
15、ion approved Oct. 1, 2015. Published November 2015. Originallyapproved in 1979. Last previous edition approved in 2014 as E691 14. DOI:10.1520/E0691-15.2For referenced ASTM standards, visit the ASTM website, www.astm.org, orcontact ASTM Customer Service at serviceastm.org. For Annual Book of ASTMSta
16、ndards volume information, refer to the standards Document Summary page onthe ASTM website.Copyright ASTM International, 100 Barr Harbor Drive, PO Box C700, West Conshohocken, PA 19428-2959. United States13.1.8 repeatability limit (r), nthe value below which theabsolute difference between two indivi
17、dual test results obtainedunder repeatability conditions may be expected to occur with aprobability of approximately 0.95 (95 %). E1773.1.9 repeatability standard deviation, (sr), nthe standarddeviation of test result obtained under repeatability conditions.E1773.1.10 reproducibility, nprecision und
18、er reproducibilityconditions. E1773.1.11 reproducibility conditions, nconditions where testresults are obtained with the same method on identical testitems in different laboratories with different operators usingdifferent equipment. E1773.1.12 reproducibility limit (R), nthe value below whichthe abs
19、olute difference between two test results obtained underreproducibility conditions may be expected to occur with aprobability of approximately 0.95 (95 %). E1773.1.13 reproducibility standard deviation (sR), nthe stan-dard deviation of test results obtained under reproducibilityconditions. E1773.1.1
20、4 ruggedness test, na planned experiment in whichenvironmental factors or test conditions are deliberately variedin order to evaluate the effects of such variation. E11693.1.15 test determination, nthe value of a characteristic ordimension of a single test specimen derived from one or moreobserved v
21、alues. E22823.1.16 test method, na definitive procedure that producesa test result. E22823.1.17 test observation, nsee observation. E22823.1.18 test result, nthe value of a characteristic obtainedby carrying out a specified test method. E22823.1.19 test specimen, nthe portion of a test unit needed t
22、oobtain a single test determination. E22823.1.20 test unit, nthe total quantity of material (containingone or more test specimens) needed to obtain a test result asspecified in the test method; see test result. E22823.2 Definitions of Terms Specific to This Standard:3.2.1 average of the cell average
23、s, x=,nthe average of thecell averages for a particular material.3.2.2 between-laboratory consistency statistic, h, ntheratio of the cell deviation to the standard deviation of the cellaverages.3.2.2.1 DiscussionThis statistic is an indicator of how onelaboratorys cell average compares with the aver
24、age of theother laboratories for a particular material (see X1.2.2).3.2.3 between-laboratory standard deviation, sL,nthesample standard deviation attributable to differences of testresult means among laboratories.3.2.4 between-laboratory variance, sL2,nthe sample vari-ance component attributable to
25、differences of test result meansamong laboratories.3.2.4.1 DiscussionThis statistic is estimated indirectlyfrom the variance of cell averages and the repeatabilityvariance. In situations where there is good agreement amonglaboratories the estimate of this variance component may beclose to zero or be
26、 negative. In the latter case, the estimate isset to zero. (See Note 2 and X1.1.2).3.2.5 cell, nthe intersection of a row and column in atwo-way classification table, in which the rows represent thelaboratories and the columns represent the materials.3.2.5.1 DiscussionThe table holds the test result
27、s from aninterlaboratory study, and each cell contains the test resultsfrom a particular laboratory on a particular material (seeSection 6 and Table 1).3.2.6 cell average, x, nthe average of the test results in aparticular cell.3.2.7 cell deviation, d, nthe cell average minus the aver-age of the cel
28、l averages.3.2.8 cell standard deviation, s, nthe standard deviation ofthe test results in a particular cell.3.2.9 repeatability variance, sr2,nthe sample variance oftest results obtained under repeatability conditions.3.2.9.1 DiscussionThis statistic is estimated for a materialas the pooled within-
29、laboratory variances over all of thelaboratories in the ILS.3.2.10 reproducibility variance, sR2,nthe sample varianceof test results obtained under reproducibility conditions.3.2.10.1 DiscussionThis statistic is estimated as the sumof the two variance components due to between-laboratories,sL2, and
30、within-laboratories, sr2.3.2.11 standard deviation of the cell averages, sx,nthestandard deviation of the cell averages for a particular material.TABLE 1 Glucose in Serum ILS Test Result DataLaboratoryMaterialABCDE1 41.0341.4541.3778.2878.1878.49132.66133.83133.10193.71193.59193.65292.78294.09292.89
31、2 41.1742.0041.1577.7880.3879.54132.92136.90136.40190.88200.14194.30292.27309.40295.083 41.0140.6842.6679.1879.7280.81132.61135.80135.36192.71193.28190.28295.53290.14292.344 39.3742.3742.6384.0878.6081.92138.50148.30135.69195.85196.36199.43295.19295.44296.835 41.8841.1941.3278.1679.5878.33131.90134.
32、14133.76192.59191.44195.12293.93292.48294.286 43.2840.5042.2878.6679.2781.75137.21135.14137.50195.34198.26198.13297.74296.80290.337 41.0841.2739.0279.7681.4577.35130.97131.59134.92194.66191.99187.13287.29293.76289.368 43.3642.6541.7280.4480.8079.80135.46135.14133.63197.56195.99200.82298.46295.28296.
33、12E691 1523.2.12 variance of the cell averages, sx2,nthe samplevariance of the cell averages for a particular material.3.2.13 within-laboratory consistency statistic, k, nthe ra-tio of the cell standard deviation to the repeatability standarddeviation.3.2.13.1 DiscussionThis statistic is an indicato
34、r of howone laboratorys cell standard deviation under repeatabilityconditions compares with the repeatability standard deviationestimated from all laboratories for a particular material (seeX1.2.3).4. Significance and Use4.1 ASTM regulations require precision statements in alltest methods in terms o
35、f repeatability and reproducibility. Thispractice may be used in obtaining the needed information assimply as possible. This information may then be used toprepare a precision statement in accordance with PracticeE177. Knowledge of the test method precision is useful incommerce and in technical work
36、 when comparing test resultsagainst standard values (such as specification limits) or be-tween data sources (different laboratories, instruments, etc.).4.1.1 When a test method is applied to a large number ofportions of a material that are as nearly alike as possible, thetest results obtained will n
37、ot all have the same value. Ameasure of the degree of agreement among these test resultsdescribes the precision of the test method for that material.Numerical measures of the variability between such test resultsprovide inverse measures of the precision of the test method.Greater variability implies
38、 smaller (that is, poorer) precisionand larger imprecision.4.1.2 Repeatability and ReproducibilityThese two termsdeal with the variability of test results obtained under specifiedlaboratory conditions and represent the two extremes of testmethod precision. Repeatability concerns the variability be-t
39、ween independent test results obtained within a single labo-ratory in the shortest practical period of time by a singleoperator with a specific set of test apparatus using testspecimens (or test units) taken at random from a single quantityof homogeneous material obtained or prepared for the ILS.Rep
40、roducibility deals with the variability between single testresults obtained in different laboratories, each of which hasapplied the test method to test specimens (or test units) takenat random from a single quantity of homogeneous materialobtained or prepared for the ILS.4.1.2.1 Repeatability Condit
41、ionsThe single-operator,single-set-of-apparatus requirement means that for a particularstep in the measurement process the same combination ofoperator and apparatus is used for every test result and on everymaterial. Thus, one operator may prepare the test specimens, asecond measure the dimensions a
42、nd a third measure thebreaking force. “Shortest practical period of time” means thatthe test results, at least for one material, are obtained in a timenot less than in normal testing and not so long as to permitsignificant changes in test material, equipment or environment.4.1.2.2 Reproducibility Co
43、nditionsThe factors that con-tribute to variability in a single laboratory, such as operator,equipment used, calibration of the equipment, and environment(for example, temperature, humidity, air pollution) will gener-ally have different effects in other laboratories, and the vari-ability among labor
44、atories will be greater .4.1.3 Precision is reported as a standard deviation, coeffi-cient of variation (relative standard deviation), variance, or aprecision limit (a data range indicating no statistically signifi-cant difference between test results).4.1.4 This practice is designed only to estimat
45、e the precisionof a test method. However, when accepted reference values areavailable for the property levels, the test result data obtainedaccording to this practice may be used in estimating the bias ofthe test method. For a discussion of bias estimation and therelationships between precision, bia
46、s, and accuracy, see Prac-tice E177.4.2 Observations, Test Determinations and Test ResultsAtest method often has three distinct stages: the direct observa-tion of dimensions or properties, the arithmetic combination ofthe observed values to obtain a test determination, and thearithmetic combination
47、of a number of test determinations toobtain the test result of the test method.4.2.1 In the simplest of test methods a single direct obser-vation is both the test determination and the test result. Forexample, the test method may require the measurement of thelength of a test specimen dimension, whi
48、ch then becomes thetest result.4.2.2 A test determination may involve a combination oftwo or more observations. For example, a test method mayrequire the measurement of the mass and the volume of the testspecimen, and then direct that the mass be divided by thevolume to obtain the density of the spe
49、cimen. The wholeprocess of measuring the mass and the volume, and calculatingthe density, is a test determination.4.2.2.1 If the test method specifies that only one testdetermination is to be made, then the test determination valueis the test result of the test method. Some test methods requirethat several determinations be made and the values obtained beaveraged or otherwise combined to obtain the test result of thetest method. Averaging of several determinations is often usedto reduce the effect of local variations of the property
