ASTM E1402-1999 Standard Terminology Relating to Sampling《抽样的相关术语》.pdf

1、Designation: E 1402 99An American National StandardStandard TerminologyRelating to Sampling1This standard is issued under the fixed designation E 1402; the number immediately following the designation indicates the year oforiginal adoption or, in the case of revision, the year of last revision. A nu

2、mber in parentheses indicates the year of last reapproval. Asuperscript epsilon (e) indicates an editorial change since the last revision or reapproval.1. Scope1.1 This terminology covers those items related to statisticalaspects of sampling.2. Referenced Documents2.1 ASTM Standards:E 105 Practice f

3、or Probability Sampling of Materials2E 456 Terminology Relating to Quality and Statistics23. Significance and Use3.1 This terminology standard is a subsidiary to Terminol-ogy E 456.3.2 It provides definitions, descriptions, discussions, andcomparison of terms.4. Terminologyacceptance quality limit (

4、AQL), n quality level that is theworst tolerable process average when a continuing series oflots is submitted for acceptance sampling.DISCUSSIONThis concept only applies when a sampling schemewith rules for switching and discontinuation such as in ISO 2859-1 orISO 3951 is used. Although individual l

5、ots with quality as bad as theacceptance quality limit may be accepted with fairly high probability,the designation of an acceptance quality limit does not suggest that thisis a desirable quality level. Sampling schemes found in internationalstandards such as ISO 2859-1, with their rules for switchi

6、ng anddiscontinuation of sampling inspection, are designed to encouragesuppliers to have process averages consistently better than AQL.Otherwise, there is a high risk that the inspection severity will beswitched to tightened inspection, under which the criteria for lotacceptance become more demandin

7、g. Once on tightened inspection,unless action is taken to improve the process, it is very likely that therule requiring discontinuation of sampling inspection pending suchimprovement will be invoked.cluster sampling, n when the primary sampling unit com-prises a bundle of elementary units or a group

8、 of subunits,the term cluster sampling may be applied.DISCUSSIONExamples of cluster sampling are: selection of cityblocks as primary sampling units; selection of a household as a clusterof people (of which only one may be interviewed); selection of a bundleof rods or pipe from a shipment; and select

9、ion, from a shipment ofcartons that contain boxes or packages within them.double sampling, na form of multi-phase sampling, inwhich there are only two phases. See phase.draw, na term used in sample selection. See step.final sample, nsample obtained at the final stage of multi-stage sampling.multi-st

10、age sampling, nested sampling sampling in whichthe sample is selected by stages, the sampling units at eachstage being from the larger sampling units chosen at theprevious stage.NOTE 1Multi-stage sampling is different from multiple sampling. (seeacceptance sampling).primary sampling unit, psu, nthe

11、element, increment,segment or cluster selected at the first stage of the selectionprocedure from a population or universe.DISCUSSIONThis concept requires that the universe (or population)has been divided into a discrete set of sampling units or can be sodivided in the process of selecting the sample

12、. Examples are cartons ofa lot or shipment, bales of wool or jute, and units created in moving abulk material such as coal or sand. These units are designated as theprimary sampling units, which may be subsampled at further stages ofthe sampling procedure.probability sample, na sample of which the s

13、ampling unitshave been selected by a chance process such that, at eachstep of selection, a specified probability of selection can beattached to each sampling unit available for selection.DISCUSSIONThese probabilities of selection need not be equal, Also,see Practice E 105 in this volume.proportional

14、 sampling, na method of selection such thatthe proportion of the sampling units (usually, psus) selectedfor the sample from each stratum is the same (except forpossible rounding effects).DISCUSSIONThe procedure for proportional sampling is to select asample from each stratum of a stratified universe

15、 (or population) suchthat (except for possible rounding effects):n sub 1/N sub 1 = n sub 2/N sub 2 = n sub g/N sub g,where:n sub i = the sample size, and1This terminology is under the jurisdiction of ASTM Committee E11 on Qualityand Statistics and is the direct responsibility of Subcommittee E11.70

16、on Editorial/Terminology.Current edition approved Nov. 10, 1999. Published February 2000. Originallypublished as E 1402 91. Last previous edition E 1402 96.2Annual Book of ASTM Standards, Vol 14.02.1Copyright ASTM International, 100 Barr Harbor Drive, PO Box C700, West Conshohocken, PA 19428-2959, U

17、nited States.N sub i = the stratum size for the ith stratum,g = the number of strataSize here refers to the number of sampling units (usually,psus) in the sample and in the stratum. See simple randomsample and probability sample for methods of selection withineach stratum.samplingprocess of drawing

18、or constituting a sample.sampling fraction, f, nthe ratio f of the number of samplingunits selected for the sample to the number of sampling unitsavailable.DISCUSSIONFor the simple random sample case, f = n/Nwhere n isthe sample size and N is the number of sampling units available. Whenf 0.10, estim

19、ation of the precision of an estimator should take accountof this magnitude of f.sampling with replacement, na procedure used with someprobability sampling plans in which a selected unit isreplaced after any step in selection so that this sampling unitis available for selection again at the next ste

20、p of selection,or at any other succeeding step of the sample selectionprocedure.sampling without replacement, na procedure in which aselected sampling unit is set aside for the sample, and apreviously unselected unit is selected at each step (or draw)of the sample selection procedure.DISCUSSIONMost

21、samplings, including simple random samplingand stratified random sampling, are conducted by sampling withoutreplacement. Computer methods have been developed for making thesample selections. See step.stratified random sample, na sample that is selectedindependently within each stratum of a universe

22、or popula-tion.DISCUSSIONThe sample selection within each stratum is usually asimple random sample, but probability sampling with unequal prob-abilities may be used, or systematic sampling may be used. Further, inorder to optimize the sampling plan, the proportion of the samplingunits selected for t

23、he sample in each stratum may or may not be thesame from one stratum to another (optimization requires taking accountof differing variances between the strata). Also, see proportionalsampling.subsample, nsample taken from a sample of a population.NOTE 2It may be selected by the same method as was us

24、ed inselecting the original sample, but need not be so.NOTE 3In sampling from bulk material, subsamples are often pre-pared by sample division. The subsample thus obtained is also called a“divided sample.” See sample division.systematic sampling, nsample selection procedure in whichevery kth element

25、 is selected from the universe or popula-tion; for example, u, u + k, u + 2k, u + 3k, etc., where u is inthe interval 1 to k.DISCUSSIONIf k = 20 and u = 7 is the initial unit selected, thensampling units, 7, 27, 47, 67, . , would comprise the sample. WhenN/k is not an integer, there is a small bias

26、due to the end effect. Whenu is selected by a chance process and N/k is an integer, the systematicsample will provide unbiased estimates of the population average ortotal. Situations for which N/k is not an integer usually ignore the smallor negligible bias in estimating the mean or total. Schemes h

27、ave beendeveloped for non-integer N/k to overcome sampling bias.Estimation of the precision of an average computed from a system-atic sample is a difficult problem that has no generally satisfactorysolution. Independent replicate systematic samples provide an approachto variance estimation, but have

28、 been rejected by some writers. In someASTM situations where replicate samples may be obtained on a routinebasis, the technique may be useful.tertiary sampling unit, nin multi-stage sampling, a subsam-pling unit selected at the 3rd stage of a sampling plan. Seestage.NOTE 4Such a unit may be further

29、subdivided to obtain a desiredmeasurement. Terminology is not uniform for labeling of units at the 4thstage or beyond.ASTM International takes no position respecting the validity of any patent rights asserted in connection with any item mentionedin this standard. Users of this standard are expressly

30、 advised that determination of the validity of any such patent rights, and the riskof infringement of such rights, are entirely their own responsibility.This standard is subject to revision at any time by the responsible technical committee and must be reviewed every five years andif not revised, ei

31、ther reapproved or withdrawn. Your comments are invited either for revision of this standard or for additional standardsand should be addressed to ASTM International Headquarters. Your comments will receive careful consideration at a meeting of theresponsible technical committee, which you may atten

32、d. If you feel that your comments have not received a fair hearing you shouldmake your views known to the ASTM Committee on Standards, at the address shown below.This standard is copyrighted by ASTM International, 100 Barr Harbor Drive, PO Box C700, West Conshohocken, PA 19428-2959,United States. Individual reprints (single or multiple copies) of this standard may be obtained by contacting ASTM at the aboveaddress or at 610-832-9585 (phone), 610-832-9555 (fax), or serviceastm.org (e-mail); or through the ASTM website(www.astm.org).E1402992