ASTM D6299-2002e1 Standard Practice for Applying Statistical Quality Assurance Techniques to Evaluate Analytical Measurement System Performance《应用统计质量保证技术来评价分析测量系统性能的标准实施规程》.pdf

《ASTM D6299-2002e1 Standard Practice for Applying Statistical Quality Assurance Techniques to Evaluate Analytical Measurement System Performance《应用统计质量保证技术来评价分析测量系统性能的标准实施规程》.pdf》由会员分享，可在线阅读，更多相关《ASTM D6299-2002e1 Standard Practice for Applying Statistical Quality Assurance Techniques to Evaluate Analytical Measurement System Performance《应用统计质量保证技术来评价分析测量系统性能的标准实施规程》.pdf（22页珍藏版）》请在麦多课文档分享上搜索。

1、Designation: D 6299 02e1An American National StandardStandard Practice forApplying Statistical Quality Assurance Techniques toEvaluate Analytical Measurement System Performance1This standard is issued under the fixed designation D 6299; the number immediately following the designation indicates the

2、year 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.e1NOTEEquation references in A1.5.4.4 were corrected editoriall

3、y in March 2006.1. Scope1.1 This practice provides information for the design andoperation of a program to monitor and control ongoing stabilityand precision and bias performance of selected analyticalmeasurement systems using a collection of generally acceptedstatistical quality control (SQC) proce

4、dures and tools.NOTE 1A complete list of criteria for selecting measurement systemsto which this practice should be applied and for determining the frequencyat which it should be applied is beyond the scope of this practice.However, some factors to be considered include (1) frequency of use ofthe an

5、alytical measurement system, (2) criticality of the parameter beingmeasured, (3) system stability and precision performance based onhistorical data, (4) business economics, and (5) regulatory, contractual, ortest method requirements.1.2 This practice is applicable to stable analytical measure-ment s

6、ystems that produce results on a continuous numericalscale.1.3 This practice is applicable to laboratory test methods.1.4 This practice is applicable to validated process streamanalyzers.NOTE 2For validation of univariate process stream analyzers, see alsoPractice D 3764.1.5 This practice assumes th

7、at the normal (Gaussian) modelis adequate for the description and prediction of measurementsystem behavior when it is in a state of statistical control.NOTE 3For non-Gaussian processes, transformations of test resultsmay permit proper application of these tools. Consult a statistician forfurther gui

8、dance and information.1.6 This practice does not address statistical techniques forcomparing two or more analytical measurement systems ap-plying different analytical techniques or equipment compo-nents that purport to measure the same property(s).2. Referenced Documents2.1 ASTM Standards:2D 3764 Pr

9、actice for Validation of Process Stream AnalyzerSystemsD 5191 Test Method for Vapor Pressure of Petroleum Prod-ucts (Mini Method)E 177 Practice for Use of the Terms Precision and Bias inASTM Test MethodsE 178 Practice for Dealing With Outlying ObservationsE 456 Terminology Relating to Quality and St

10、atisticsE 691 Practice for Conducting an Interlaboratory Study toDetermine the Precision of a Test Method3. Terminology3.1 Definitions:3.1.1 accepted reference value, na value that serves as anagreed-upon reference for comparison and that is derived as (1)a theoretical or established value, based on

11、 scientific principles,(2) an assigned value, based on experimental work of somenational or international organization, such as the U.S. Na-tional Institute of Standards and Technology (NIST), or (3)aconsensus value, based on collaborative experimental workunder the auspices of a scientific or engin

12、eering group.(E 456/E 177)3.1.2 accuracy, nthe closeness of agreement between anobserved value and an accepted reference value. (E 456/E 177)3.1.3 assignable cause, na factor that contributes tovariation and that is feasible to detect and identify. (E 456)3.1.4 bias, na systematic error that contrib

13、utes to thedifference between a population mean of the measurements ortest results and an accepted reference or true value. (E 456/E 177)3.1.5 control limits, nlimits on a control chart that areused as criteria for signaling the need for action or for judging1This practice is under the jurisdiction

14、of ASTM Committee D02 on PetroleumProducts and Lubricants and is the direct responsibility of Subcommittee D02.94 onQuality Assurance and Statistics.Current edition approved June 10, 2002. Published September 2002. Originallypublished as D 629998. Last previous edition D 629900.2For referenced ASTM

15、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.1Copyright ASTM International, 100 Barr Harbor Drive, PO Box C700, West Conshohock

16、en, PA 19428-2959, United States.whether a set of data does or does not indicate a state ofstatistical control. (E 456)3.1.6 lot, na definite quantity of a product or materialaccumulated under conditions that are considered uniform forsampling purposes. (E 456)3.1.7 precision, nthe closeness of agre

17、ement between testresults obtained under prescribed conditions. (E 456)3.1.8 repeatability conditions, nconditions where mutu-ally independent test results are obtained with the same testmethod in the same laboratory by the same operator with thesame equipment within short intervals of time, using t

18、estspecimens taken at random from a single sample of material.(E 456, E 177)3.1.9 reproducibility conditions, nconditions under whichtest results are obtained in different laboratories with the sametest method, using test specimens taken at random from thesame sample of material. (E 456, E 177)3.2 D

19、efinitions of Terms Specific to This Standard:3.2.1 analytical measurement system, na collection of oneor more components or subsystems, such as samplers, testequipment, instrumentation, display devices, data handlers,printouts or output transmitters, that is used to determine aquantitative value of

20、 a specific property for an unknownsample in accordance with a test method.3.2.1.1 DiscussionAn analytical measurement systemmay comprise multiple instruments being used for the sametest method.3.2.2 blind submission, nsubmission of a check standardor quality control (QC) sample for analysis without

21、 revealingthe expected value to the person performing the analysis.3.2.3 check standard, nin QC testing, a material havingan accepted reference value used to determine the accuracy ofa measurement system.3.2.3.1 DiscussionA check standard is preferably a mate-rial that is either a certified referenc

22、e material with traceabilityto a nationally recognized body or a material that has anaccepted reference value established through interlaboratorytesting. For some measurement systems, a pure, single com-ponent material having known value or a simple gravimetric orvolumetric mixture of pure component

23、s having calculablevalue may serve as a check standard. Users should be awarethat for measurement systems that show matrix dependencies,accuracy determined from pure compounds or simple mixturesmay not be representative of that achieved on actual samples.3.2.4 common (chance, random) cause, nfor qua

24、lity as-surance programs, one of generally numerous factors, individu-ally of relatively small importance, that contributes to varia-tion, and that is not feasible to detect and identify.3.2.5 double blind submission, nsubmission of a checkstandard or QC sample for analysis without revealing the che

25、ckstandard or QC sample status and expected value to the personperforming the analysis.3.2.6 expected value, nfor a QC sample analyzed using anin-statistical control measurement system, the estimate of thetheoretical limiting value to which the average of results tendswhen the number of results appr

26、oaches infinity.3.2.7 in-statistical-control, adja process, analytical mea-surement system, or function that exhibits variations that canonly be attributable to common cause.3.2.8 proficiency testing, ndetermination of a laboratorystesting capability by participation in an interlaboratory cross-chec

27、k program.3.2.8.1 DiscussionASTM Committee D02 conducts pro-ficiency testing among hundreds of laboratories, using a widevariety of petroleum products and lubricants.3.2.9 quality control (QC) sample, nfor use in qualityassurance programs to determine and monitor the precision andstability of a meas

28、urement system, a stable and homogeneousmaterial having physical or chemical properties, or both,similar to those of typical samples tested by the analyticalmeasurement system. The material is properly stored to ensuresample integrity, and is available in sufficient quantity forrepeated, long term t

29、esting.3.2.10 site precision (R8), nthe value below which theabsolute difference between two individual test results obtainedunder site precision conditions may be expected to occur witha probability of approximately 0.95 (95 %). It is defined as 2.77times the standard deviation of results obtained

30、under siteprecision conditions.3.2.11 site precision conditions, nconditions under whichtest results are obtained by one or more operators in a singlesite location practicing the same test method on a singlemeasurement system which may comprise multiple instru-ments, using test specimens taken at ra

31、ndom from the samesample of material, over an extended period of time spanningat least a 15 day interval.3.2.11.1 DiscussionSite precision conditions should in-clude all sources of variation that are typically encounteredduring normal, long term operation of the measurement sys-tem. Thus, all operat

32、ors who are involved in the routine use ofthe measurement system should contribute results to the siteprecision determination. If multiple results are obtained withina 24h period, then it is recommended that the number ofresults used in site precision calculations be increased tocapture the longer t

33、erm variation in the system.3.2.12 site precision standard deviation, nthe standarddeviation of results obtained under site precision conditions.3.2.13 validation audit sample, na QC sample or checkstandard used to verify precision and bias estimated fromroutine quality assurance testing.3.3 Symbols

34、:3.3.1 ARVaccepted reference value.3.3.2 EWMAexponentially weighted moving average.3.3.3 Iindividual observation (as in I-chart).3.3.4 MRmoving range.3.3.5 MR average of moving range.3.3.6 QCquality control.3.3.7 R8site precision.3.3.8 sR8site precision standard deviation.3.3.9 VAvalidation audit.3.

35、3.10 x2chi squared.3.3.11 llambda.D629902e124. Summary of Practice4.1 QC samples and check standards are regularly analyzedby the measurement system. Control charts and other statisticaltechniques are presented to screen, plot, and interpret testresults in accordance with industry-accepted practices

36、 to as-certain the in-statistical-control status of the measurementsystem.4.2 Statistical estimates of the measurement system preci-sion and bias are calculated and periodically updated usingaccrued data.4.3 In addition, as part of a separate validation auditprocedure, QC samples and check standards

37、 may be submittedblind or double-blind and randomly to the measurement systemfor routine testing to verify that the calculated precision andbias are representative of routine measurement system perfor-mance when there is no prior knowledge of the expected valueor sample status.5. Significance and Us

38、e5.1 This practice can be used to continuously demonstratethe proficiency of analytical measurement systems that areused for establishing and ensuring the quality of petroleum andpetroleum products.5.2 Data accrued, using the techniques included in thispractice, provide the ability to monitor analyt

39、ical measurementsystem precision and bias.5.3 These data are useful for updating test methods as wellas for indicating areas of potential measurement system im-provement.6. Reference Materials6.1 QC samples are used to establish and monitor theprecision of the analytical measurement system.6.1.1 Sel

40、ect a stable and homogeneous material havingphysical or chemical properties, or both, similar to those oftypical samples tested by the analytical measurement system.NOTE 4When the QC sample is to be utilized for monitoring aprocess stream analyzer performance, it is often helpful to supplement thepr

41、ocess analyzer system with a subsystem to automate the extraction,mixing, storage, and delivery functions associated with the QC sample.6.1.2 Estimate the quantity of the material needed for eachspecific lot of QC sample to (1) accommodate the number ofanalytical measurement systems for which it is

42、to be used(laboratory test apparatuses as well as process stream analyzersystems) and (2) provide determination of QC statistics for auseful and desirable period of time.6.1.3 Collect the material into a single container and isolateit.6.1.4 Thoroughly mix the material to ensure homogeneity.6.1.5 Con

43、duct any testing necessary to ensure that the QCsample meets the characteristics for its intended use.6.1.6 Package or store QC samples, or both, as appropriatefor the specific analytical measurement system to ensure thatall analyses of samples from a given lot are performed onessentially identical

44、material. If necessary, split the bulkmaterial collected in 6.1.3 into separate and smaller containersto help ensure integrity over time. (WarningTreat thematerial appropriately to ensure its stability, integrity, andhomogeneity over the time period for which it is to stored andused. For samples tha

45、t are volatile, such as gasoline, storage inone large container that is repeatedly opened and closed canresult in loss of light ends. This problem can be avoided bychilling and splitting the bulk sample into smaller containers,each with a quantity sufficient to conduct the analysis. Simi-larly, samp

46、les prone to oxidation can benefit from splitting thebulk sample into smaller containers that can be blanketed withan inert gas prior to being sealed and leaving them sealed untilthe sample is needed.)6.2 Check standards are used to estimate the accuracy of theanalytical measurement system.6.2.1 A c

47、heck standard may be a commercial standardreference material when such material is available in appropri-ate quantity, quality and composition.NOTE 5Commercial reference material of appropriate compositionmay not be available for all measurement systems.6.2.2 Alternatively, a check standard may be p

48、repared froma material that is analyzed under reproducibility conditions bymultiple measurement systems. The accepted reference value(ARV) for this check standard shall be the average afterstatistical examination and outlier treatment has been applied.36.2.2.1 Exchange samples circulated as part of

49、an interlabo-ratory exchange program, or round robin, may be used as checkstandards. For an exchange sample to be usable as a checkstandard, the standard deviation of the interlaboratory ex-change program shall not be statistically greater than thereproducibility standard deviation for the test method. AnF-test should be applied to test acceptability.NOTE 6The uncertainty in the ARV is inversely proportional to thesquare root of the number of values in the average. This practicerecommends that a minimum of 16 non-outlier results be used i