1、Designation:D663105(Reapproved 2015)Standard Guide forCommittee D01 for Conducting an Interlaboratory Study forthe Purpose of Determining the Precision of a Test Method1This standard is issued under the fixed designation D6631;the number immediately following the designation indicates the year ofori
2、ginal adoption or,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.1.Scope1.1 This guide covers a simplified statistical procedure forplanning and
3、conducting interlaboratory evaluations of testmethods.2.Referenced Documents2.1 ASTM Standards:2E177 Practice for Use of the Terms Precision and Bias inASTM Test MethodsE456 Terminology Relating to Quality and StatisticsE691 Practice for Conducting an Interlaboratory Study toDetermine the Precision
4、of a Test MethodE1345 Practice for Reducing the Effect of Variability ofColor Measurement by Use of Multiple Measurements3.Significance and Use3.1 The purpose of an interlaboratory evaluation,as definedin this guide,is to determine the variability of results obtainedin different laboratories on equi
5、valent equipment using aprescribed test method.3.2 The definitions of statistical terms used in this guide arecontained in Terminology E456.4.Problem Formulation4.1 The objective of the evaluation should be to clearlydefine the expected precision of the test method.Within thecurrent limits of both t
6、he software,and the statistical protocolscurrently available,this effectively restricts the use of thisguide to test methods which yield results that are continuous.This generally means a measured quantity,such as pH orbrightness.Results that are discrete(such as counts or pass-fail),or ordered(rank
7、ed),present three special problems in thecreation of a meaningful precision statement:4.1.1 The amount of information contained in discrete andordered data is much less than in continuous data,necessitatingthe collection of much more data.4.1.2 The sensitivity(the ability to discriminate betweensimi
8、lar samples)is much less in discrete and ordered data thancontinuous data.4.1.3 Since the precision statement relies on the normaldistribution,and the distributions of discrete and ordered dataare usually decidedly non-normal,the normal precision state-ment is invalid.4.2 Given these concerns with d
9、iscrete and ordered data,asimple statement of the results obtained in these types ofstudies might be the most useful information for a prospectiveuser of a test method.5.Preliminary5.1 Flow chart the test method.5.2 Survey known sources of information related to the testmethod to establish how resul
10、ts are affected by variations inoperating conditions,atmospheric conditions,differences be-tween operators,etc.Select what appears to be the optimumprocedure.5.3 Provide instructions for the test method and,withoutcomment,observe a laboratory technician perform a testaccording to these instructions.
11、Revise any parts of the draftcausing difficulty.5.4 If desirable,make a comparative study with other testmethods for measuring the property by using specimens with awide range of values of the property under test(and possiblywith wide ranges in other properties).6.Preparation for Interlaboratory Stu
12、dy6.1 Prepare a clear statement of the type of informationrequired from the interlaboratory evaluation.6.2 Based on the study made in one laboratory(Section 5),prepare a proposed master plan for the interlaboratory evalu-ation.Discuss the plan,in an open meeting,if possible,withother participants in
13、 the study.1This guide is under the jurisdiction of ASTM Committee D01 on Paint andRelated Coatings,Materials,and Applications and is the direct responsibility ofSubcommittee D01.20 on Quality Assurance and Statistics.Current edition approved Dec.1,2015.Published December 2015.Originallyapproved in
14、2001.Last previous edition approved in 2011 as D6631 05(2011).DOI:10.1520/D6631-05R15.2For 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
15、 onthe ASTM website.Copyright ASTM International,100 Barr Harbor Drive,PO Box C700,West Conshohocken,PA 19428-2959.United States1 6.3 Select the materials to be used in the interlaboratoryevaluations so as to:6.3.1 Cover the applicable range of the property or compo-nent to be measured,and6.3.2 Repr
16、esent as many classes of materials as feasible,towhich the test method will be applied.7.Pilot Evaluation7.1 If the test method is new or the procedure for an old testmethod is greatly altered,a pilot study by one laboratoryinvolving a few materials(two or three)may reveal seriouslymisleading directions in the written procedure.A Box andWhisker Plot(as outlined in Practice E1345),or a Violin Plot3may help to clarify this evaluation.8.Participating Laboratory Qualification8.1 It is important that
