ASTM E456-2008e1 838 Standard Terminology Relating to Quality and Statistics.pdf

1、Designation: E 456 081An American National StandardStandard TerminologyRelating to Quality and Statistics1This standard is issued under the fixed designation E 456; the number immediately following the designation indicates the year oforiginal adoption or, in the case of revision, the year of last r

2、evision. 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 Department of Defense.1NOTENew terms were added and other terms corrected edi

3、torially in January 2009.1. Scope1.1 This standard is the general terminology standard forterms defined in the standards of Committee E11 on Qualityand Statistics.1.2 A term in this standard which lists an attribution to anE11 technical standard indicates that the standard is normativefor that term.

4、 Any changes in the term definition in thenormative standard will be editorially changed in this standard.Any terms added to an E11 standard will be editorially addedto this standard with an attribution to that standard.1.3 Term definitions that are similar to ISO 3534 will benoted in this standard,

5、 but ISO 3534 will not be considerednormative for any E11 terms.2. Referenced Documents2.1 ASTM E11 Standards with terms in this standard:2E29 Practice for Using Significant Digits in Test Data toDetermine Conformance with SpecificationsE 177 Practice for Use of the Terms Precision and Bias inASTM T

6、est MethodsE 178 Practice for Dealing With Outlying ObservationsE 1169 Practice for Conducting Ruggedness TestsE 1325 Terminology Relating to Design of ExperimentsE 1402 Guide for Sampling DesignE 1488 Guide for Statistical Procedures to Use in Develop-ing and Applying Test MethodsE 1994 Practice fo

7、r Use of Process Oriented AOQL andLTPD Sampling PlansE 2234 Practice for Sampling a Stream of Product byAttributes Indexed by AQLE 2281 Practice for Process and Measurement CapabilityIndicesE 2282 Guide for Defining the Test Result of a Test MethodE 2334 Practice for Setting an Upper Confidence Boun

8、d Fora Fraction or Number of Non-Conforming items, or a Rateof Occurrence for Non-conformities, Using Attribute Data,When There is a Zero Response in the SampleE 2489 Practice for Statistical Analysis of One-Sample andTwo-Sample Interlaboratory Proficiency Testing ProgramsE 2554 Practice for Estimat

9、ing and Monitoring the Uncer-tainty of Test Results of a Test Method in a SingleLaboratory Using a Control Sample ProgramE 2555 Practice for Factors and Procedures forApplying theMIL-STD-105 Plans in Life and Reliability InspectionE 2586 Practice for Calculating and Using Basic StatisticsE 2587 Prac

10、tice for Use of Control Charts in StatisticalProcess ControlE 2655 Guide for Reporting Uncertainty of Test Results andUse of the Term Measurement Uncertainty in ASTM TestMethods2.2 ISO Standards:ISO 3534 Statistics-Vocabulary and SymbolsPart 1: Probability and General Statistical TermsPart 2: Applie

11、d Statistics3. Terminologyacceptance quality limit AQL , nquality limit that is theworst tolerable process average when a continuing series oflots is submitted for acceptance sampling. E 2234accepted reference value, na value that serves as anagreed-upon reference for comparison, and which is derive

12、das: (1) a theoretical or established value, based on scientificprinciples, (2) an assigned or certified value, based onexperimental work of some national or international organi-zation, or (3) a consensus or certified value, based oncollaborative experimental work under the auspices of ascientific

13、or engineering group. E 177accuracy, nthe closeness of agreement between a test resultand an accepted reference value. E 1771This terminology is under the jurisdiction ofASTM Committee E11 on Qualityand Statistics and is the direct responsibility of Subcommittee E11.70 on Editorial/Terminology.Curre

14、nt edition approved April 1, 2008. Published June 2008. Originallyapproved in 1972. Last previous edition approved in 2006 as E 456 06e1.2For referenced ASTM standards, visit the ASTM website, www.astm.org, orcontact ASTM Customer Service at serviceastm.org. For Annual Book of ASTMStandardsvolume in

15、formation, refer to the standards Document Summary page onthe ASTM website.1Copyright ASTM International, 100 Barr Harbor Drive, PO Box C700, West Conshohocken, PA 19428-2959, United States.aliases, nin a fractional factorial design, two or more effectswhich are estimated by the same contrast and wh

16、ich,therefore, cannot be estimated separately. E 1325area sampling, nprobability sampling in which a map,rather than a tabulation of sampling units, serves as thesampling frame. E 1402assignable cause, nfactor that contributes to variation in aprocess or product output that is feasible to detect and

17、identify (see special cause). E 2587attributes data, nobserved values or test results that indi-cate the presence or absence of specific characteristics orcounts of occurrences of events in time or space. E 2587attributes, method of, nmeasurement of quality by themethod of attributes consists of not

18、ing the presence (orabsence) of some characteristic or attribute in each of theunits in the group under consideration, and counting howmany units do (or do not) possess the quality attribute, orhow many such events occur in the unit, group, or area.E 2334average outgoing quality (AOQ)the average per

19、cent defec-tive of outgoing product including all accepted lots orbatches, after any defective units found in them are replacedby acceptable units, plus all lots or batches which are notaccepted after such lots or batches have been effectively100 % inspected and all defective units replaced by accep

20、t-able units. E 1994average outgoing quality limit (AOQL)the maximum oftheAOQs for all possible incoming percentages defective forthe process, for a given acceptance sampling plan. E 1994average quality protectiona type of protection in whichthere is prescribed some chosen value of average percentde

21、fective in the product after inspection (average outgoingquality limit (AOQL), that shall not be exceeded in the longrun no matter what may be the level of percent defective inthe product submitted to the inspector. E 1994average run length (ARL)the average number of times thata process will have be

22、en sampled and evaluated before ashift in process level is signaled. E 2587average standard deviation, s, narithmetic average ofsample standard deviations. E 2281balanced incomplete block design (BIB), nan incompleteblock design in which each block contains the same numberk of different versions fro

23、m the t versions of a singleprincipal factor arranged so that every pair of versionsoccurs together in the same number, l, of blocks from the bblocks. E 1325batch, in inspection, na collection of units of productproduced under conditions that are considered uniform andfrom which a sample is drawn an

24、d inspected, and may differfrom a collection of units designated as a batch for otherpurposes, for example, production, shipment, etc. E 2234batch size, nthe number of units of product in a batch.E 2234bias, nthe difference between the expectation of the testresults and an accepted reference value.

25、E 177bulk sampling, nsampling to prepare a portion of a mass ofmaterial that is representative of the whole. E 1402c chartcontrol chart that monitors the count of occurrencesof an event in a defined increment of time or space.E 2587center lineline on a control chart depicting the average levelof the

26、 statistic being monitored. E 2587chance cause source of inherent random variation in aprocess which is predictable within statistical limits (seecommon cause). E 2587characteristic, na property of items in a sample or popula-tion which, when measured, counted or otherwise observed,helps to distingu

27、ish between the items. E 2282check samplesee control sample. E 2554classification of defects, nthe enumeration of possibledefects of the unit of product arranged according to theirseriousness, that is, critical, major, or minor defect.E 2234cluster sampling, nsampling in which the sampling unitconsi

28、sts of a group of subunits, all of which are measured forsampled clusters E 1402coefficient or variation, CVfor a nonnegative characteristic,the ratio of the standard deviation to the mean for apopulation or sample. . E 2586collaborative study, ninterlaboratory study in which eachlaboratory uses the

29、 defined method of analysis to analyzeidentical portions of homogeneous materials to assess theperformance characteristics obtained for that method ofanalysis. E 2489collaborative trial, nsee collaborative study. E 2489common causesee chance cause. E 2587completely randomized design, na design in wh

30、ich thetreatments are assigned at random to the full set of experi-mental units. E 1325completely randomized factorial design, na factorial ex-periment (including all replications) run in a completelyrandomized design. E 1325composite design, na design developed specifically forfitting second order

31、response surfaces to study curvature,constructed by adding further selected treatments to thoseobtained from a 2nfactorial (or its fraction). E 1325confidence bound, nsee confidence limit. E 2334confidence coefficient, nthe value, C, of the probabilityassociated with a confidence interval or statist

32、ical coverageinterval. It is often expressed as a percentage. ISO 3534-1E 2334confidence interval, nan interval estimate of a populationparameter, calculated such that there is a given long-runprobability that the parameter is included in the interval.E 2334confidence level, nsee confidence coeffici

33、ent. E 2334confidence limit, nthe upper or lower limit of a confidenceinterval for a population parameter. E 2334confounded factorial design, na factorial experiment inwhich only a fraction of the treatment combinations are runin each block and where the selection of the treatmentcombinations assign

34、ed to each block is arranged so that oneE4560812or more prescribed effects is(are) confounded with the blockeffect(s), while the other effects remain free from confound-ing. E 1325confounding, ncombining indistinguishably the main effectof a factor or a differential effect between factors (interac-t

35、ions) with the effect of other factor(s), block factor(s) orinteractions(s). E 1325consumers riskthe probability that a lot whose percentagedefective is equal to the LTPD will be accepted by the plan.E 1994contrast, na linear function of the observations for whichthe sum of the coefficients is zero.

36、 E 1325contrast analysis, na technique for estimating the param-eters of a model and making hypothesis tests on preselectedlinear combinations of the treatments (contrasts). E 1325control chart , n-chart on which are plotted a statisticalmeasure of a subgroup versus time of sampling along withlimits

37、 based on the statistical distribution of that measure soas to indicate how much common, or chance, cause variationis inherent in the process or product. E 2587control chart factor, na tabulated constant, depending onsample size, used to convert specified statistics or parametersinto a central line

38、value or control limit appropriate to thecontrol chart. E 2587control limits, nlimits on a control chart that are used ascriteria for signaling the need for action or judging whethera set of data does or does not indicate a state of statisticalcontrol based on a prescribed degree of risk. E 2587cont

39、rol sample, nsample taken from a stable, homogeneousmaterial for the purposes of monitoring the performance ofa test method in a laboratory. E 2554critical defect, na defect that judgment and experienceindicate would result in hazardous or unsafe conditions forindividuals using, maintaining, or depe

40、nding upon the prod-uct, or a defect that judgment and experience indicate islikely to prevent performance of the function of a major enditem. E 2234critical defective, na unit of product which contains one ormore critical defects and may also contain major and/orminor defects. E 2234defect, nany no

41、nconformance of the unit of product withspecified requirements. E 2234defective, na unit of product which contains one or moredefects. E 2234defects per hundred units, nany given quantity of units ofproduct is one hundred times the number of defects con-tained therein (one or more defects being poss

42、ible in any unitof product) divided by the total number of units of product,that is:Defects per hundred units 5Number of defects 3100Number of units inspectedE 2234dependent variable, nSee response variable. E 1325design of experiments, nthe arrangement in which anexperimental program is to be condu

43、cted, and the selectionof the levels (versions) of one or more factors or factorcombinations to be included in the experiment. Synonymsinclude experiment design and experimental design.E 1325double sampling plan, na multiple sampling plan in whichup to two samplings can be taken and evaluated to acc

44、ept orreject a lot. E 2555empirical percentile, nestimate of a population percentileusing the sample data. This is a sample value such that apercentage p of the sample is less than that value. E 2586error of result, na test result minus the accepted referencevalue of the characteristic. E 2655expand

45、ed uncertainty, U, nuncertainty reported as a mul-tiple of the standard uncertainty. E 2655evolutionary operation (EVOP), na sequential form ofexperimentation conducted in production facilities duringregular production. E 1325experimental design, nsee design of experiments. E 1325experiment space, n

46、the materials, equipment, environmen-tal conditions and so forth that are available for conductingan experiment. E 1325experimental unit, na portion of the experiment space towhich a treatment is applied or assigned in the experiment.E 1325factorial experiment (general), nin general, an experimentin

47、 which all possible treatments formed from two or morefactors, each being studied at two or more levels (versions)are examined so that interactions (differential effects) as wellas main effects can be estimated. E 13252nfactorial experiment, na factorial experiment in which nfactors are studied, eac

48、h of them in two levels (versions).E 1325fractional factorial design, na factorial experiment inwhich only an adequately chosen fraction of the treatmentsrequired for the complete factorial experiment is selected tobe run. E 1325frame, na list, compiled for sampling purposes, whichdesignates all of

49、the sampling units (items or groups) of apopulation or universe to be considered in a specific study.E 1402fully nested experiment, na nested experiment in which thesecond factor is nested within levels (versions) of the firstfactor and each succeeding factor is nested within versionsof the previous factor. E 1325hierarchical experiment, nsee nested experiment.E 1325histogram, ngraphical representation of the frequency dis-tribution of a characteristic consisting of a set of rectangleswith area proportional to