1、Designation: D 6300 07An American National StandardStandard Practice forDetermination of Precision and Bias Data for Use in TestMethods for Petroleum Products and Lubricants1This standard is issued under the fixed designation D 6300; the number immediately following the designation indicates the yea
2、r oforiginal adoption or, in the case of revision, the year of last revision. A number in parentheses indicates the year of last reapproval. Asuperscript epsilon (e) indicates an editorial change since the last revision or reapproval.INTRODUCTIONBoth Research Report RR:D021007,2Manual on Determining
3、 Precision Data for ASTM Methodson Petroleum Products and Lubricants2and the ISO 4259, benefitted greatly from more than 50 yearsof collaboration between ASTM and the Institute of Petroleum (IP) in the UK. The more recent workwas documented by the IP and has become ISO 4259.ISO 4259 encompasses both
4、 the determination of precision and the application of such precisiondata. In effect, it combines the type of information in RR:D0210072regarding the determination ofthe precision estimates and the type of information in Practice D 3244 for the utilization of test data.The following practice, intend
5、ed to replace RR:D021007,2differs slightly from related portions ofthe ISO standard. This new practice is consistent with the computer software, ADJD6300 D2PP,Version 4.43, Determination of Precision and Bias Data for Use in Test Methods for PetroleumProducts.31. Scope1.1 This practice covers the ne
6、cessary preparations andplanning for the conduct of interlaboratory programs for thedevelopment of estimates of precision (determinability, repeat-ability, and reproducibility) and of bias (absolute and relative),and further presents the standard phraseology for incorporatingsuch information into st
7、andard test methods.1.2 This practice is generally limited to homogeneous prod-ucts with which serious sampling problems do not normallyarise.1.3 This practice may not be suitable for solid or semisolidproducts such as petroleum coke, industrial pitches, paraffinwaxes, greases, or solid lubricants w
8、hen the heterogeneousproperties of the substances create sampling problems. In suchinstances, use Practice E 691 or consult a trained statistician.1.4 A software program (ADJD6300) performs the neces-sary computations prescribed by this practice.2. Referenced Documents2.1 ASTM Standards:4D 123 Termi
9、nology Relating to TextilesD 3244 Practice for Utilization of Test Data to DetermineConformance with SpecificationsE29 Practice for Using Significant Digits in Test Data toDetermine Conformance with SpecificationsE 456 Terminology Relating to Quality and StatisticsE 691 Practice for Conducting an In
10、terlaboratory Study toDetermine the Precision of a Test Method2.2 ISO Standards:ISO 4259 Petroleum Products-Determination and Applica-tion of Precision Data in Relation to Methods of Test52.3 ASTM Adjuncts:ADJD6300 D2PP, Version 4.43, Determination of Preci-sion and Bias Data for Use in Test Methods
11、 for PetroleumProducts33. Terminology3.1 Definitions:1This practice is under the jurisdiction of ASTM Committee D02 on PetroleumProducts and Lubricants and is the direct responsibility of Subcommittee D02.94 onCoordinating Subcommittee on Quality Assurance and Statistics.Current edition approved Jul
12、y 1, 2007. Published September 2007. Originallyapproved in 1998. Last previous edition approved in 2006 as D 630006.2Supporting data have been filed at ASTM International Headquarters and maybe obtained by requesting Research Report RR:D021007.3Available from ASTM International Headquarters. Order A
13、djunct No.ADJD6300.4For referenced ASTM standards, visit the ASTM website, www.astm.org, orcontact ASTM Customer Service at serviceastm.org. For Annual Book of ASTMStandards volume information, refer to the standards Document Summary page onthe ASTM website.5Available from International Organization
14、 for Standardization, 1 rue deVaremb, Case postale 56, CH-1211 Geneva 20, Switzerland.1Copyright ASTM International, 100 Barr Harbor Drive, PO Box C700, West Conshohocken, PA 19428-2959, United States.3.1.1 analysis of variance (ANOVA), na procedure fordividing the total variation of a set of data i
15、nto two or moreparts, one of which estimates the error due to selecting andtesting specimens and the other part(s) possible sources ofadded variation. D 1233.1.2 bias, nthe difference between the population meanof the test results and an accepted reference value. E 4563.1.3 bias, relative, nthe diff
16、erence between the popula-tion mean of the test results and an accepted reference value,which is the agreed upon value obtained using an acceptedreference method for measuring the same property.3.1.4 degrees of freedom, nthe divisor used in the calcu-lation of variance.3.1.4.1 DiscussionThis definit
17、ion applies strictly only inthe simplest cases. Complete definitions are beyond the scopeof this practice. ISO 42593.1.5 determinability, na quantitative measure of the vari-ability associated with the same operator in a given laboratoryobtaining successive determined values using the same appa-ratu
18、s for a series of operations leading to a single result; it isdefined as that difference between two such single determinedvalues as would be exceeded in the long run in only one casein 20 in the normal and correct operation of the test method.3.1.5.1 DiscussionThis definition implies that two deter
19、-mined values, obtained under determinability conditions,which differ by more than the determinability value should beconsidered suspect. If an operator obtains more than twodeterminations, then it would usually be satisfactory to checkthe most discordant determination against the mean of theremaind
20、er, using determinability as the critical difference (1).63.1.6 mean square, nin analysis of variance, a contractionof the expression “mean of the squared deviations from theappropriate average(s)” where the divisor of each sum ofsquares is the appropriate degrees of freedom. D 1233.1.7 normal distr
21、ibution, nthe distribution that has theprobability function:fx! 5 1/s!2p!21/2exp 2 x !2/2s2# (1)where:x = a random variate, = the mean distribution, ands = the standard deviation of the distribution.(Syn. Gaussian distribution, law of error) D 1233.1.8 outlier, na result far enough in magnitude from
22、other results to be considered not a part of the set.RR:D02100723.1.9 precision, nthe degree of agreement between two ormore results on the same property of identical test material. Inthis practice, precision statements are framed in terms ofrepeatability and reproducibility of the test method.3.1.9
23、.1 DiscussionThe testing conditions represented byrepeatability and reproducibility should reflect the normalextremes of variability under which the test is commonly used.Repeatability conditions are those showing the least variation;reproducibility, the usual maximum degree of variability. Referto
24、the definitions of each of these terms for greater detail.RR:D02100723.1.10 random error, nthe chance variation encounteredin all test work despite the closest control of variables.RR:D02100723.1.11 repeatability, nthe quantitative expression of therandom error associated with the same operator in a
25、 givenlaboratory obtaining repetitive results by applying the same testmethod with the same apparatus under constant operatingconditions on identical test material within short intervals oftime. It is defined as the difference between two such results atthe 95 % confidence level. RR:D02100723.1.11.1
26、 DiscussionInterpret as the value equal to orbelow which the absolute difference between two single testresults obtained in the above conditions may expect to lie witha probability of 95 %. ISO 42593.1.11.2 DiscussionThe difference is related to the repeat-ability standard deviation but it is not th
27、e standard deviation orits estimate. RR:D02100723.1.12 reproducibility, na quantitative expression of therandom error associated with different operators from differentlaboratories using different apparatus, each obtaining a singleresult by applying the same test method on an identical testsample. I
28、t is defined as the 95 % confidence limit for thedifference between two such single and independent results.3.1.12.1 DiscussionInterpret as the value equal to orbelow which the absolute difference between two single testresults on identical material obtained by operators in differentlaboratories, us
29、ing the standardized test, may be expected to liewith a probability of 95 %. ISO 42593.1.12.2 DiscussionThe difference is related to the repro-ducibility standard deviation but is not the standard deviationor its estimate. RR:D02100723.1.12.3 DiscussionIn those cases where the normal useof the test
30、method does not involve sending a sample to atesting laboratory, either because it is an in-line test method orbecause of serious sample instabilities or similar reasons, theprecision test for obtaining reproducibility may allow for theuse of apparatus from the participating laboratories at acommon
31、site (several common sites, if feasible). The statisticalanalysis is not affected thereby. However, the interpretation ofthe reproducibility value will be affected, and therefore, theprecision statement shall, in this case, state the conditions towhich the reproducibility value applies.3.1.13 standa
32、rd deviation, nthe most usual measure of thedispersion of observed values or results expressed as thepositive square root of the variance. E 4563.1.14 sum of squares, nin analysis of variance, a con-traction of the expression “sum of the squared deviations fromthe appropriate average(s)” where the a
33、verage(s) of interestmay be the average(s) of specific subset(s) of data or of theentire set of data. D 1233.1.15 variance, na measure of the dispersion of a seriesof accepted results about their average. It is equal to the sum ofthe squares of the deviation of each result from the average,divided b
34、y the number of degrees of freedom.RR:D02100726The bold numbers in parentheses refers to the list of references at the end of thisstandard.D63000723.1.16 variance, between-laboratory, nthat component ofthe overall variance due to the difference in the mean valuesobtained by different laboratories. I
35、SO 42593.1.16.1 DiscussionWhen results obtained by more thanone laboratory are compared, the scatter is usually wider thanwhen the same number of tests are carried out by a singlelaboratory, and there is some variation between means obtainedby different laboratories. Differences in operator techniqu
36、e,instrumentation, environment, and sample “as received” areamong the factors that can affect the between laboratoryvariance. There is a corresponding definition for between-operator variance.3.1.16.2 DiscussionThe term “between-laboratory” is of-ten shortened to “laboratory” when used to qualify re
37、presen-tative parameters of the dispersion of the population of results,for example as “laboratory variance.”3.2 Definitions of Terms Specific to This Standard:3.2.1 determination, nthe process of carrying out a seriesof operations specified in the test method whereby a singlevalue is obtained.3.2.2
38、 operator, na person who carries out a particular test.3.2.3 probability density function, nfunction which yieldsthe probability that the random variable takes on any one of itsadmissible values; here, we are interested only in the normalprobability.3.2.4 result, nthe final value obtained by followi
39、ng thecomplete set of instructions in the test method.3.2.4.1 DiscussionIt may be obtained from a single de-termination or from several determinations, depending on theinstructions in the method. When rounding off results, theprocedures described in Practice E29shall be used.4. Summary of Practice4.
40、1 A draft of the test method is prepared and a pilotprogram can be conducted to verify details of the procedureand to estimate roughly the precision of the test method.4.2 A plan is developed for the interlaboratory study usingthe number of participating laboratories to determine thenumber of sample
41、s needed to provide the necessary degrees offreedom. Samples are acquired and distributed. The interlabo-ratory study is then conducted on an agreed draft of the testmethod.4.3 The data are summarized and analyzed. Any depen-dence of precision on the level of test result is removed bytransformation.
42、 The resulting data are inspected for uniformityand for outliers. Any missing and rejected data are estimated.The transformation is confirmed. Finally, an analysis of vari-ance is performed, followed by calculation of repeatability,reproducibility, and bias. When it forms a necessary part of thetest
43、 procedure, the determinability is also calculated.5. Significance and Use5.1 ASTM test methods are frequently intended for use inthe manufacture, selling, and buying of materials in accordancewith specifications and therefore should provide such precisionthat when the test is properly performed by
44、a competentoperator, the results will be found satisfactory for judging thecompliance of the material with the specification. Statementsaddressing precision and bias are required in ASTM testmethods. These then give the user an idea of the precision ofthe resulting data and its relationship to an ac
45、cepted referencematerial or source (if available). Statements addressing deter-minability are sometimes required as part of the test methodprocedure in order to provide early warning of a significantdegradation of testing quality while processing any series ofsamples.5.2 Repeatability and reproducib
46、ility are defined in theprecision section of every Committee D02 test method. Deter-minability is defined above in Section 3. The relationshipamong the three measures of precision can be tabulated interms of their different sources of variation (see Table 1).5.2.1 When used, determinability is a man
47、datory part of theProcedure section. It will allow operators to check theirtechnique for the sequence of operations specified. It alsoensures that a result based on the set of determined values isnot subject to excessive variability from that source.5.3 Abias statement furnishes guidelines on the re
48、lationshipbetween a set of test results and a related set of acceptedreference values. When the bias of a test method is known, acompensating adjustment can be incorporated in the testmethod.5.4 This practice is intended for use by D02 subcommitteesin determining precision estimates and bias stateme
49、nts to beused in D02 test methods. Its procedures correspond withISO 4259 and are the basis for the Committee D02 computersoftware, Calculation if Precision Data: Petroleum Test Meth-ods. The use of this practice replaces that of Research ReportRR:D021007.25.5 Standard practices for the calculation of precision havebeen written by many committees with emphasis on theirparticular product area. One developed by Committee E11 onStatistics is Practice E 691. Practice E 691 and this practicediffer as outlined in Table 2.6. Stages in Plann
