ANSI ASTM D7372-2012 Standard Guide for Analysis and Interpretation of Proficiency Test Program Results《熟练试验程序结果的分析和说明用标准指南》.pdf

《ANSI ASTM D7372-2012 Standard Guide for Analysis and Interpretation of Proficiency Test Program Results《熟练试验程序结果的分析和说明用标准指南》.pdf》由会员分享，可在线阅读，更多相关《ANSI ASTM D7372-2012 Standard Guide for Analysis and Interpretation of Proficiency Test Program Results《熟练试验程序结果的分析和说明用标准指南》.pdf（24页珍藏版）》请在麦多课文档分享上搜索。

1、Designation: D7372 12 An American National StandardStandard Guide forAnalysis and Interpretation of Proficiency Test ProgramResults1This standard is issued under the fixed designation D7372; the number immediately following the designation indicates the year oforiginal adoption or, in the case of re

2、vision, 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.1. Scope*1.1 This guide covers the analysis and interpretation ofproficiency test (PT) program results. For pa

3、rticipants ininterlaboratory proficiency test (PT) (or crosscheck, checkscheme, etc.) programs, this guide describes procedures forassessing participants results relative to the PT programresults and potentially improving the laboratorys testingperformance based on the assessment findings and insigh

4、ts. Forthe committees responsible for the test methods included ininterlaboratory proficiency testing programs, this guide de-scribes procedures for assessing industrys ability to performtest methods and for potentially identifying needs for methodimprovement.1.2 This standard does not purport to ad

5、dress all of thesafety concerns, if any, associated with its use. It is theresponsibility of the user of this standard to establish appro-priate safety and health practices and determine the applica-bility of regulatory limitations prior to use.2. Referenced Documents2.1 ASTM Standards:2D1266 Test M

6、ethod for Sulfur in Petroleum Products (LampMethod)D2622 Test Method for Sulfur in Petroleum Products byWavelength Dispersive X-ray Fluorescence SpectrometryD4294 Test Method for Sulfur in Petroleum and PetroleumProducts by Energy Dispersive X-ray Fluorescence Spec-trometryD4951 Test Method for Dete

7、rmination of Additive Elementsin Lubricating Oils by Inductively Coupled PlasmaAtomic Emission SpectrometryD5185 Test Method for Multielement Determination ofUsed and Unused Lubricating Oils and Base Oils byInductively Coupled Plasma Atomic Emission Spectrom-etry (ICP-AES)D5453 Test Method for Deter

8、mination of Total Sulfur inLight Hydrocarbons, Spark Ignition Engine Fuel, DieselEngine Fuel, and Engine Oil by Ultraviolet FluorescenceD6259 Practice for Determination of a Pooled Limit ofQuantitationD6299 Practice for Applying Statistical Quality Assuranceand Control Charting Techniques to Evaluat

9、e AnalyticalMeasurement System PerformanceD6617 Practice for Laboratory Bias Detection Using SingleTest Result from Standard MaterialD6792 Practice for Quality System in Petroleum Productsand Lubricants Testing LaboratoriesD7039 Test Method for Sulfur in Gasoline, Diesel Fuel, JetFuel, Kerosine, Bio

10、diesel, Biodiesel Blends, andGasoline-Ethanol Blends by Monochromatic WavelengthDispersive X-ray Fluorescence SpectrometryE177 Practice for Use of the Terms Precision and Bias inASTM Test MethodsE456 Terminology Relating to Quality and StatisticsE2655 Guide for Reporting Uncertainty of Test Results

11、andUse of the Term Measurement Uncertainty in ASTM TestMethods3. Terminology3.1 Definitions:3.1.1 accuracy, ncloseness of agreement between an ob-served value and an accepted reference value. E177, E4563.1.2 assignable cause, nfactor that contributes to varia-tion and that is feasible to detect and

12、identify. E4563.1.3 bias, nsystematic error that contributes to the differ-ence between a population mean of the measurements or testresults and an accepted reference or true value. E177, E4563.1.4 control limits, nlimits on a control chart that areused as criteria for signaling the need for action

13、or for judgingwhether a set of data does or does not indicate a state ofstatistical control. E4563.1.5 in-statistical-control, adjprocess, analytical mea-surement system, or function that exhibits variations that canonly be attributable to common cause. D62991This guide is under the jurisdiction of

14、ASTM Committee D02 on PetroleumProducts, Liquid Fuels, and Lubricants and is the direct responsibility of Subcom-mittee D02.94 on Coordinating Subcommittee on Quality Assurance and Statistics.Current edition approved April 15, 2012. Published October 2012. Originallyapproved in 2007. Last previous e

15、dition approved in 2007 as D737207. DOI:10.1520/D7372-12.2For 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.*A S

16、ummary of Changes section appears at the end of this standardCopyright ASTM International, 100 Barr Harbor Drive, PO Box C700, West Conshohocken, PA 19428-2959. United States13.1.6 Interlaboratory Crosscheck Program (ILCP),nASTM International Proficiency Test Program sponsoredby Committee D02 on Pet

17、roleum Products and Lubricants, seeASTM website for current details.3.1.7 proficiency testing, ndetermination of a laboratorystesting capability by participation in an interlaboratory cross-check program D62993.1.8 uncertainty, nan indication of the magnitude of errorassociated with a value that tak

18、es into account both systematicerrors and random errors associated with the measurement ortest process. E26553.1.9 Z-score, nstandardized and dimensionless measureof the difference between an individual result in a data set andthe arithmetic mean of the dataset, re-expressed in units ofstandard devi

19、ation of the dataset (by dividing the actualdifference from the mean by the standard deviation for the dataset). D62993.1.10 Z-score, nmeasure similar to the Z-score exceptthat the PT program standard deviation is replaced with onethat takes into account the site precision of the laboratory. Z isa v

20、alid approach when the laboratorys site precision standarddeviation is less than the PT program (that is, these datastandard deviation ) or stated otherwise when the TPI 1.Z 5Xi2 X!Ss!21Ssthese data2nDDwhere:Z = site precision adjusted Z-Score,Xi= laboratorys result,X = PT average value,s = site pre

21、cision standard deviation estimate, andsthese data= PT Program standard deviation estimate.3.2 Definitions of Terms Specific to This Standard:3.2.1 common (chance, random) cause, nfor quality as-surance programs, one of generally numerous factors, individu-ally of relatively small importance, that c

22、ontributes tovariation, and that is not feasible to detect or control. D62993.2.2 site precision (R), nvalue below which the absolutedifference between two individual test results obtained undersite precision conditions may be expected to occur with aprobability of approximately 0.95 (95 %). It is d

23、efined as 2.77times the standard deviation of results obtained under siteprecision conditions. D62993.2.3 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

24、may comprise multipleinstruments, using test specimens taken at random from thesame sample of material, over an extended period of timespanning at least a 15-day interval. D62993.2.4 these test data, nterm used by the ASTM Interna-tional D02 PT program to identify statistical results calculatedfrom

25、the data submitted by program participants.3.3 Symbols:3.3.1 Iindividual observation (as in I-chart).3.3.2 QCquality control.3.3.3 Rsite precision.4. Summary of Guide4.1 Petroleum and petroleum product samples are regularlyanalyzed by specified standard test methods as part of aproficiency test prog

26、ram. This guide provides a laboratory withthe tools and procedures for evaluating their results from thePT program. Techniques are presented to screen, plot, andinterpret test results in accordance with industry-acceptedpractices.5. Significance and Use5.1 This guide can be used to evaluate the perf

27、ormance of alaboratory or group of laboratories participating in an inter-laboratory proficiency test (PT) program involving petroleumand petroleum products.5.2 Data accrued, using the techniques included in thisguide, provide the ability to monitor analytical measurementsystem precision and bias. T

28、hese data are useful for updatingstandard test methods, as well as for indicating areas ofpotential measurement system improvement for action by thelaboratory. This guide serves both the individual participatinglaboratory and the responsible standards development group asfollows:5.2.1 Tools and Appr

29、oaches for Participating Laboratories.Administrative ReviewsFlagged Data and InvestigationsData Normality ChecksHistogramsBias (Deviation from Mean)Z-ScoresTPI (Industry)PTP and Site Precision Comparisons5.2.2 Tools and Approaches for Responsible Standards De-velopment Groups.TPI and precision trend

30、sBias via box participantsshould exercise caution in planning actions for flaggeddataAD 1 this is strong evidence of inadequate variation in thedataset due to inadequate numerical resolution (Couldalso arise from un-removed outliers or a perversely non-normal data distribution)6.3.2 In addition, gra

31、phical tools are available for evaluatingnormality. For example, use a normal probability or a q-q plot(an equivalent plot to the normal probability plot) to visuallyassess the validity of the normality assumption. Refer toPractice D6299 for guidance regarding the preparation andinterpretation of no

32、rmal probability plots and correspondingAD statistics. If data are normally distributed, the normalprobability plot should be approximately linear. Major devia-tions from linearity are an indication of nonnormal distribu-tions. The appearance of a series of steps in the plotted datarather than a smo

33、oth line is an indication that the data (ormeasurement) resolution is too coarse relative to the precisionof the test method. A few examples of these normal probabilityplots are shown in parallel with histograms in X3.1.6.4 Histograms:6.4.1 Plotting PT data as histograms is a useful graphicaltool fo

34、r viewing data distribution and variability. The ILCPprogram plots histograms for all data sets where n 20; andincludes the mean and the 1st and 99th percentile limits on thehistogram for data sets with n 30. These limits are based on“median 6 2.33 Robust Standard Deviation,” where 62.33are respecti

35、vely the first and 99th percentiles of the standardnormal distribution.6.4.2 PT participants should review histograms when avail-able and note unusual data distributions. Participants shouldlocate where their result falls within the histogram bins.Depending on the histogram, the location of data in

36、certain binscould indicate a potential issue such as bias. Consider review-ing the histogram in parallel with corresponding statistics suchas the Z-score, AD statistic, TPI (Industry) and the normalprobability (or deviate) plot. See X3.1 for examples.6.5 Bias (Deviation from Mean):6.5.1 As mentioned

37、 in Practice D6299, subsection 7.6,evaluate proficiency test results by plotting the signed devia-tions from the mean for each result for each test cycle. PracticeD6299 suggests plotting the signed deviations from the con-sensus value (robust mean) on control charts. Laboratorieswould then apply the

38、 run rule strategy outlined in that standardto identify outliers and other issues such as long-term biases.The recommended control chart is a chart of individualD7372 123observations (called an I-Chart) with an exponentiallyweighted moving average (EWMA) overlaid on the data. SeeX3.2 for examples.6.

39、5.2 Another graphical approach for monitoring bias in-volves use of Box and Whisker graphs. As is the case forreviewing histograms, laboratories should use the Box andWhisker graphs to observe where their particular result lies inthe graph relative to the general distribution of results for thetest

40、method they used. Consider investigating any data outsidethe whisker end, if those data were not flagged already forother causes.Areview of the apparent distribution of results foreach test method measuring the same parameter may providevaluable insight regarding overall biases between methods. See7

41、.2 for more information on box and whisker plots.6.5.3 Another statistical approach for evaluating bias isdescribed in D6617. This guide estimates whether or not asingle test result is biased compared to the consensus valuefrom the PT program.6.6 Z-scoreThe Z-score calculated for each datum submit-t

42、ed by the laboratory should be reviewed with respect to thefollowing:6.6.1 Sign and Magnitude of Z-scoreThe sign (that is, “+”or “”) of the statistic reflects the relative bias of the individualresult versus the mean of the sample group. Z-score valuesfalling in the ranges of plus or minus 0-1, 1 to

43、 2, 2 to 3, and 3can be compared to control chart values falling in the rangesbetween the mean and 1-sigma, 1 to 2-sigma, 2 to 3-sigma, and 3-sigma. For normally distributed data, there is an expecta-tion that about 68% of the data will lie in the -1 sigma to +1sigma range, about 95% in the -2 sigma

44、 to +2 sigma range, and99% in the -3 to +3 sigma range. The further a laboratorysZ-score is from zero, the greater the relative bias and lower theprobability that the data is considered within statistical control.Conduct investigations to determine the cause of any perceivedbias as needed.6.6.2 Tren

45、d of Z-scores from Previous RoundsRecord theZ-score values for each test method (parameter) for successivePT program rounds on a control chart to show the trend overtime. The lab can use the run rules promulgated in PracticeD6299 to evaluate any observed trends. Conduct investigationsto determine ca

46、uses as needed. The ILCP uses the PrecisionIndicator (PI) statistic (ratio of the Pooled Z-score StandardDeviation to the average Z-score standard deviation for a givenlaboratory) to assist laboratories in assessing Z-scores. TheILCP program team also adopted PI = 0.8 as the critical valuefor taking

47、 action. If the resulting calculation produces a PI 3 (or 1.0.7. ProcedureAnalysis and Interpretation by StandardsDevelopment Group7.1 This section covers the analysis and interpretation ofproficiency test data by a committee or working group chargedTABLE 1 General TPI ImplicationsTPI (Industry) Res

48、ult Implication 1.2 The performance of the group providing data is probably satisfactory relative to the corresponding ASTM published precision.0.8 to 1.2 The performance of the group providing data may be marginal and each laboratory should consider reviewing the testmethod procedures to identify o

49、pportunities for improvement.6 3) and evaluate the factors that may be contribut-ing to this performance. This may involve targeting theselaboratories with questionnaires to gather appropriate informa-tion. Consultation with test method experts is generally helpfulin interpreting results from these investigations.8. Report8.1 Laboratories and working groups should document theirinvestigations. In the spirit of continuous improvement, labo-ratories and working groups are encouraged to share theirfindings from their investigations and analyses.