Ch.7SelectingsamplesTheneedtosampleOverviewofSamplingtechniquesProbabilitysamplingNon-probabilitysamplingDefinitionoftermsCensusCollectandanalysedatafromeverypossiblecaseorgroupmemberSamplingArangeofmethodsthatenableresearchertoreducetheamountofdatabyonlydatafromasubgroupratherthanallpossiblecasesorelementsPopulationThefullsetofcasesfromwhichasampleistakenFigure7.1Population,sampleandindividualcases1.TheneedtosampleBudgetconstraintspreventyoufromsurveyingtheentirepopulationTimeconstraintspreventyoufromsurveyingtheentirepopulationImpracticabletosurveytheentirepopulationYouhavecollectedallthedatabutneedtheresultsquickly2.OverviewofsamplingtechniquesProbabilityorrepresentativesampling-Eachcasefrompopulationisknownandusuallyisequalforallcases -(surveyandexperimentalresearchstrategies)Non-probabilityorjudgementalsampling-Probabilityofeachcasefromthepopulationisunknown -Impossibletoanswerresearchquestionsortoaddressobjectivesthatrequireyoutomakestatisticalinferencesaboutthecharacteristicsofthepopulation -(casestudystrategy)非隨機(jī)抽樣和隨機(jī)抽樣的比較

抽樣方法作用抽樣原則誤差判斷應(yīng)用優(yōu)缺點(diǎn)非隨機(jī)抽樣研究總體的局部現(xiàn)象非隨機(jī)抽出樣本，主觀性強(qiáng)不能計(jì)算和判斷抽樣誤差可隨時(shí)隨地采用不夠科學(xué)規(guī)范，但省錢、省事、靈活方便隨機(jī)抽樣以部分推斷總體隨機(jī)抽出樣本，客觀性強(qiáng)不能計(jì)算和判斷抽樣誤差只能定期采用科學(xué)規(guī)范，但費(fèi)時(shí)、費(fèi)錢、不夠靈活方便Figure7.2Samplingtechniques隨機(jī)抽樣非隨機(jī)抽樣簡單隨機(jī)抽樣系統(tǒng)抽樣分層抽樣分群抽樣多步抽樣配額抽樣雪球抽樣便利抽樣自選抽樣目的抽樣極端抽樣同質(zhì)抽樣不均勻抽樣典型抽樣關(guān)鍵抽樣3.ProbabilitysamplingProcessofprobabilitysampling(2)decideonasuitablesamplesize

(3)selectthemostappropriatesamplingtechnique

andselectthesample (4)checkthesampleisrepresentativeofthepopulation(1)identifyasuitablesamplingframe

basedonyourresearchquestionsorobjectivesSampleframeAcompletelistofallthecasesinthepopulationfromwhichyoursamplewillbedrawnSamplesizethenumberofcasesusedfortheresearchanalysisStatisticalinference

aprobableconclusionaboutapopulationonthebasisofdataofsampleLawoflargenumberLargersamplesizecanbetterrepresentthepopulationthanSmallersamplesizeHowtochoosethesamplesize?Theconfidenceyouneedtohaveinyourdata:thelevelofcertaintythatthesamplecanrepresentthetotalpopulation (confidence↑samplesize↓)Themarginoferrorthatyoucantolerate:theaccuracyyourequireforanyestimatesmadefromyoursample(accuracy↑samplesize↓)Thetypesofanalysisyouwillundertake: (Categories↑samplesize↑;minimumthresholdofeachtechnique)ThesizeoftotalpopulationfromwhichyoursampleisbeingdrawnResponserateReasonsofnon-response:Unreachable;ineligible;inability；refusal;totalnumberofresponsesTotalResponserate=----------------------------------totalnumberinsample-ineligibletotalnumberofresponsesActiveResponserate=------------------------------------------totalnumberinsample–(ineligible+unreachable)Population,samplingframe,samplesSelectappropriatesamplingtechniqueFivemainsamplingtechniques(1)simplerandom(2)systematic(3)stratifiedrandom(4)cluster(5)multi-stagesamplingtechnique(1)Simplerandomsampling(a)Numbereachcaseinyoursamplingframewithauniquenumber(b)Selectcasesusingrandomnumbersuntilyouractualsamplesizeisreached(pp218;587for““Randomnumbertables”).samplingtechnique(2)Systematicsampling(a)Numbereachcaseinyoursamplingframeatregularintervals(b)Selectthefirstcaseusingarandomnumber(c)calculatethesamplingfraction(抽樣比)(d)selectsubsequentcasessystematicallyusingthesamplingfractiontodeterminethefrequencyofselectionactualsamplesizeSamplingfraction=-----------------------------totalpopulationSamplingfraction:Theproportionofthetotalpopulationthatyouneedtoselect.1.Decideonsamplesize:n2.DivideframeofNindividualsintongroupsofkindividuals:samplingfractionk=n/N3.Randomlyselectoneindividualfromthe1stgroup4.Selectevery1/k-thindividualthereafterSystematicSampleN=64n=81/k=8FirstGroupsamplingtechnique(3)Stratifiedrandomsampling[‘str?tifaid](a)choosethestratificationvariable(s)(b)dividethesamplingframeintothediscretestrata(c)numbereachofthecaseswithineachstratumwithauniquenumber(d)selectyoursampleusingeithersimplerandomorsystematicsamplingStratifiedSample1.DividePopulationintoSubgroupsMutuallyExclusiveExhaustiveAtLeast1CommonCharacteristicofInterest2.SelectSimpleRandomSamplesfromSubgroupsAllStudentsPart-timeFull-timeSamplesamplingtechnique(4)Clustersampling(a)Choosetheclustergroupingforyoursamplingframe(b)numbereachoftheclusterswithauniquenumber.Thefirstclusterisnumbered0,thesecond1,andsoon(c)selectyoursampleusingsomeformofrandomsamplingClusterSample1.DividePopulationintoClustersIfManagersareElementsthenCompaniesareClusters2.RandomlySelectClusters3.SurveyAlloraRandomSampleofElementsinClusterCompanies(Clusters)Samplesamplingtechnique(5)Multi-stagesamplingOverviewofprobabilitysampleQuotasamplingPurposivesamplingSnowballsamplingSelf-selectionsamplingConveniencesampling4.Non-probabilitysampling4.Non-probabilitysampling(1)Quotasampling(a)dividethepopulationintospecificgroups(b)calculateaquotaforeachgroupbasedonrelevantandavailabledata(c)giveeachintervieweranassignment,whichstatesthenumberofcasesineachquotafromwhichtheymustcollectdata(d)combinethedatacollectedbyinterviewertoprovidethefullsampleSamples4.Non-probabilitysampling（2）Purposivesampling(judgementalsampling)Useresearcher’sjudgementonsampling(a)extremecasesamplingextremecasewillberelevantinunderstandingandexplainmoretypicalcases.E.g.studyonexcellentstudents(b)heterogeneoussamplingcompletedifferentcases,maximumvariationwillbeparticularinterestandvalueandwillrepresentthekeythemes.E.g.studyallspecialstudents(c)homogeneoussamplingenableyoutostudythegroupingreatdepth.E.g.studyonallstu.withIELTS6.0.(d)criticalcasesamplingifithappensinonecriticalcase,canithappenstoeveryone.E.g.studyonasuccessfulstu.withlowentrancegrade.(e)typicalcasesamplingillustrateaprofilewitharepresentativecase.E.g.studyanormalstu.withaveragestudyperformance4.Non-probabilitysampling（3）Snowballsampling(a)makecontactwithoneortwocasesinthepopulation(b)askthesecasestoidentifyfurthercases(c