《社会研究方法双语教学ppt课件.ppt》由会员分享，可在线阅读，更多相关《社会研究方法双语教学ppt课件.ppt（139页珍藏版）》请在taowenge.com淘文阁网|工程机械CAD图纸|机械工程制图|CAD装配图下载|SolidWorks_CaTia_CAD_UG_PROE_设计图分享下载上搜索。
1、社会研究方法双语教学课件Chapter 1 introduction l Whatissocialresearch?Wayofknowingsocialrealitybydirectexperiencel Definitionl Thedifferencesbetween“socialresearch”and“社会调查研究“Functions or purposesof social researchl Description(描述)Amajorpurposeofmanysocialscientificstudiesistodescribesituationsandevents.Therese
2、archerobservesandthendescribeswhatwasobserved.Sincescientificobservationsiscarefulanddeliberate,however,scientificdescriptionsaretypicallymoreaccurateandprecisethancasualdescriptions.(P73)Examplesl 北京汽车市场调查农村居民收入差距Explanation(解释)l Thesecondgeneralpurposesofsocialscientificresearchistoexplainthings.R
3、eportingthevotingintentionsofanelectorateisadescriptiveactivity,butreportingwhysomepeopleplantovoteforcandidateAandothersforcandidateBisanexplanatoryactivity.Reportingwhysomecitieshavehighercrimeratesthanothersisacaseofexplanation,butsimplyreportingthedifferentcrimeratesisacaseofdescription.Predicti
4、on(预测)l Forexample,thegoalofregressionanalysisisfindouttherelationshipbetweentwoormorevariables.2.Types of research methodsl Objetctivedimension A.Census(普查).l Anenumeration(列举)ofthecharacteristicsofsomepopulation(总体).Acensusisoftensimilartoasurvey,withthedifferencethatthecensuscollectsdatafromallme
5、mbersofthepopulationwhilethesurveyislimitedtoasample.B.B.Sampling survey(抽样调查)l Carefulprobabilitysamplingprovidesagroupofrespondentswhosecharacteristicsmaybetakentoreflectthoseofthelargerpopulation,andcarefullyconstructedstandardizedquestionnairesprovidedatainthesameformfromallrespondents.C.Case st
6、udy(个案研究)l Takeonlyseveralmembersfromthepopulationandstudythemindetail.Purposive Dimension descriptivestudies(描述性研究)explanatorystudies(解释性研究)time dimension.l Cross-sectionalStudy(横剖研究).Astudythatisbasedonobservationsrepresentingasinglepointintime.l LongitudinalStudy（纵贯研究）.Astudydesigninvolvingthecol
7、lectionofdataatdifferentpointsintime,ascontrastedwithacross-sectionalstudy.l Longitudinalstudiesaredesignedtopermitobservationsoveranextendedperiod.Threetypesoflongitudinalstudiesshouldbenotedhere.l Trend studies(趋势研究)arethosethatstudychangeswithinsomegeneralpopulationovertime.Exampleswouldbeacompar
8、isonofU.S.Censusovertime,showinggrowthinthenationalpopulation,oraseriesofGallupPollsduringthecourseofanelectioncampaign,showingtrendsintherelativestrengthsandstandingofdifferentcandidates.l Cohort Studies(同期群研究)examinemorespecificsubpopulations(cohorts)astheychangeovertime.Typically,acohortisanagegr
9、oup,suchasthosepeoplebornduringthe1920s,butitcanalsobebasedonsomeothertimegrouping,suchaspeopleattendingcollegeduringtheVietnamWar,peoplewhogotmarriedin1964,andsoforth.l Anexampleofcohortstudywouldbeaseriesofnationalsurveys,conductedperhapsevery10years,tostudytheeconomicattitudesofthecohortborndurin
10、gthedepressionoftheearly1930s.asampleofpersons20-25yearsofagemightbesurveyedin1960,andanothersampleofthose40-45yearsofagein1970.Althoughthespecificsetofpeoplestudiedineachofthosesurveyswouldbedifferent,eachsamplewouldrepresentthesurvivorsofthecohortbornbetween1930and1935.l Panel Studies(定组研究,追踪研究)ar
11、esimilartotrendandcohortstudiesexceptthatthesamesetofpeopleisstudiedeachtime.Oneexamplewouldbeavotingstudyinwhichthesamesampleofvoterswasinterviewedeverymonthduringanelectioncampaignandaskedforwhomtheywouldintendedtovote.Suchastudywouldmakeitpossibletoanalyzeoveralltrendsinvoterpreferencesfordiffere
12、ntcandidates,butitwouldhavetheaddedadvantageofshowingtheprecisepatternsofpersistenceandchangeinintentions.l Forexample,atrendstudythatshowedthatCandidatesAandBeachhadexactlyhalfofthevotersonSeptemberfirstandonOctoberfirstaswellcouldindicatethatnoneoftheelectoratehadchangedvotingplans,thatallofthevot
13、ershadchangedtheirintentions,orsomethingbetween.ApanelstudywouldeliminatethisconfusionbyshowingwhatkindsofvotersswitchedfromAtoBandwhatkindsswitchedfromBtoA,aswellasotherfacts.Procedures of social researchl Preparatorystage(准备阶段)l Datacollectionstage(收集资料阶段)l Analysisstage(分析阶段)l Summarystage(总结阶段)C
14、hapter 2 research designChapter 2 research designl 1.Choosearesearchproject a)Howtochoosearesearchprojectl b)Factorsrelatingwithresearchprojectchoice c)Principlesregardingresearchprojectchoicel 2.PreliminaryExplorationl a)Literaturereviewl b)Filedobservationl 3.ResearchProjectDesign a)Researchhypoth
15、esis b)Researchplan2.1 Literature Reviewl 1.PurposesofLiteratureReview Toavoidredundantresearchandtrytomakenewcontributions Toprovidebasesforhypothesis Totakeotherresearchesasreferencesforyourresearchplanl 2.HowtoReviewLiterature Snowballmethod:accordingtothereferencesandnotesoftheexistingliterature
16、tolookformorerelatedliterature Electronicresources2.2 Field Observationl Methods:colloquia(座谈会）,interview,refertoliteraturel Purpose1:forquestionnairedesignl Example:howtomeasurepeasantfamilyincomeintothreelevels:“high”,“medium”and“low”l Purpose2:forhypothesisl Example:EconomicdevelopmentImplementat
17、ionofelectoralsystemVillagersparticipation3.Research Project Designl 3.1ResearchHypothesis Hypothesis:Anexpectationaboutthenatureofthingsderivedfromatheory.Functionsofhypothesis:l Toguildaresearchl Torelatetheoreticalconceptswithempiricaldatal Toexplorenewtheoreticalknowledge Principlesformakinghypo
18、thesisl Consistentwithexistingtheoriesl Consistentwithconfirmedfactsl Canbeverifiedbyexperience3.2 Research Project Designl Purposesl Populationandobjectsl Samplingmethodsl Methodsofdatacollectionanddataanalysisl Organizationl Budgetandfacilitiesl Wages,travellingexpenses,expenseforcopyingandprintin
19、gl Facilities:camera,taperecorder,computerl TimetableChapter 3 Samplingl 3.1IntroductiontoSamplingl 1.Thehistoryofsamplingl 2.Samplingconceptsandterminologyl 3.2ProbabilitySampling(随机抽样）l 1.Simplerandomsampling(SRS)简单随机抽样l 2.Systematicsampling 系统抽样l 3.Stratifiedsampling 分层抽样l 4.Clustersampling 整群抽样l
20、 5.Multi-stagesampling 多段抽样l 3.3Non-ProbabilitySampling（非随机抽样）l 1.Purposiveorjudgmentsampling 立意抽样l 2.Quotasampling 配额抽样l 3.Snowballsampling 滚雪球抽样3.1 Introduction to Sampling 3.1 Introduction to Samplingl 1.Thehistoryofsampling PoliticalpollingbyLiteracy Digest In1920,Digesteditorsmailedpostcardstop
21、eopleinsixstates,askingthemwhotheywereplanningtovoteforinthepresidentialcampaignbetweenWarrenHardingandJamesCox.Nameswereselectedforthepollfromtelephone directories and automobile registration lists.Basedonthepostcardssentback,theDigestcorrectlypredictedthatHardingwouldbeelected.Inelectionsthatfollo
22、wed,themagazineexpandedthesizeofitspoll,andmadecorrectpredictionsin1924,1928,and1932.In1936,basedontwomillionrespondentsanswers,theDigestpredictedthatRepublicancandidateAlfLandonwouldget57%ballotsandincumbentPresidentFranklinRooseveltwouldgetonly43%.Twoweekslater,votersgaveRooseveltathirdterminoffic
23、ebythelargestlandslideinhistory,with61percentofthevote.Theproblemlayinthesamplingframeused:telephonesubscribersandautomobileowners.Suchasamplingdesignselectedadisproportionatelywealthypeople,especiallycomingonthetailendoftheworsteconomicdepressioninthenationhistory.3.1 Introduction to Samplingl(cont
24、inued)l IncontrasttotheLiteracy Digest,GeorgeGallupcorrectlypredictedthatRooseveltwouldbeatLandon.Gallupssuccessin1936hingedonhisuseofquotasampling.l Quotasamplingisbasedonaknowledgeofthecharacteristicsofthepopulationbeingsampled:whatproportionaremen,whatproportionwomen,whatproportionsareofvariousin
25、comes,ages,etc.Peopleareselectedtomatchthepopulationcharacteristics.3.1 Introduction to Sampling2.Sampling Concepts and Terminology 2.Sampling Concepts and Terminology(1)(1)i.1.Element（研 究 单 位）.An element is that unitabout which information is collected and which providesthebasisofanalysis.Typically
26、,in survey research,elements are people orcertaintypesofpeople.However,otherkindsofunitscanconstitutetheelementsforsocialresearch;families,socialclubs,or corporations might be the elements of a study.(Note:Elementsandunitsofanalysisareoftenthesameinagivenstudy,thoughtheformerreferstosampleselectionw
27、hilethelatterreferstodataanalysis.)2.Sampling Concepts and Terminology(2)(2)l 1.Population(总 体).A population is the theoretically specifiedaggregationofstudyelements.For example,specifying the term“college students”would include aconsideration of full-time and part-time students,degree candidates an
28、dnon-degree candidates,undergraduate and graduate students,and similarissues.l 2.Study Population（研 究 总 体）.A study population is thataggregationofelementsfromwhichthesampleisactuallyselected.Asapracticalmatter,youareseldominapositiontoguaranteethateveryelement meeting the theoretical definitions lai
29、d down actually has achanceofbeingselectedinthesample.Evenwherelistsofelementsexistforsamplingpurposes,thelistsareusuallysomewhatincomplete.Somestudents are always omitted,inadvertently,from student roster.Sometelephone subscribers request that their names and numbers be unlisted.Thestudypopulation,
30、then,istheaggregationofelementsfromwhichthesampleisselected.2.Sampling Concepts and Terminology(3)(3)l 3.SamplingUnit（抽 样 单 位）.Asamplingunitisthatelementorsetofelementsconsideredforselectioninsomestageofsampling.In a simple,single-stage sample,the sampling units are the same as theelements.In more c
31、omplex samples,however,different levels of samplingunits may be employed.For example,you might select a sample of censusblocksinacity,thenselectasampleofhouseholdsontheselectedblocks,andfinallyselectasampleofadultsfromselectedhouseholds.l 4.Sampling Frame（抽 样 框）.A sampling frame is the actual list o
32、fsampling units from which the sample,or some stage of the sample,isselected.l 5.ObservationUnit（观 察 单 位）.An observationunit,or unitof datacollection,isanelementsfromwhichinformationiscollected.Again,the unit of analysis and unit of observation are often the sametheindividual personbut that need not
33、 be the case.Thus the researcher mayinterview heads of households(the observation unit)to collect informationaboutallfamilymembersofthehouseholds(theunitsofanalysis).2.Sampling Concepts and Terminology(4)(4)l 6.Variable（变 量）.A variable is a set of mutually exclusiveattributes:sex,age,employmentstatu
34、s,andsoforth.l 7.Parameter（参 数 值）.Aparameteristhesummarydescriptionofagivenvariableinapopulation.l 8.Statistic（统 计 值）.A statistic is the summary description of agiven variable in a sample.Sample statistics are used to makeestimatesofpopulationparameters.l 9.SamplingError（抽样误差）.Probabilitysamplingmet
35、hodsseldom,ifever,providestatisticsexactlyequaltotheparametersthattheyareusedtoestimate.Probabilitytheory,however,permitsustoestimatethedegreeoferrortobeexpectedforagivensampledesign.2.Sampling Concepts and Terminology(5)(5)l 10.ConfidenceLevelsandConfidenceIntervals（显著性水平与置信区间）.We express the accur
36、acy of our sample statistics interms of a level of confidence that the statistics fallwithinaspecifiedintervalfromtheparameter.Forexample,wemaysayweare95percentconfidentthatoursamplestatisticsarewithinplusorminus5percentagepointsofthepopulationparameter.3.2 Probability Sampling(1)(1)l Simple Random
37、Sampling(简 单 随 机 抽 样).Atype of probability sample in which the unitscomposing a population are assigned numbers,asetofrandomnumbersisthengenerated,andtheunits having those numbers are included in thesample.Although probability theory and thecalculationsitprovidesassumethisbasicsamplingmethod,itissel
38、domusedforpracticalreasons.3.2 Probability Sampling(2)(2)l Systematic Sampling(系 统 抽 样).A type of probabilitysample in which every kth unit in a list is selected forinclusion in the sample:e.g.,every 25th student in thecollege directory of students.K is computed by dividingthesizeofthepopulationbyth
39、edesiredsamplesizeandiscalled the sampling interval.Within certain constraints,systematic sampling is a functional equivalent of simplerandomsamplingandusuallyeasiertodo.l Samplinginterval=populationsize/samplesizel samplingratio=samplesize/populationsize 3.2 Probability Sampling(3)(3)Stratified sam
40、pling(分 层 抽 样):toorganizethepopulationintohomogeneoussubsets(withheterogeneity between subsets.)and to selecttheappropriatenumberofelementsfromeach.3.2 Probability Sampling(4)l ClusterSampling(整群抽样).Amultistagesampleinwhichnaturalgroups(clusters)aresampledinitially,withthemembersofeachselectedgroupb
41、eingsubsampledafterward.Forexample,youmightselectasampleofU.S.collegesanduniversitiesfromadirectory,getlistsofthestudentsatalltheselectedschools,thendrawsamplesofstudentsfromeach.3.3 Non-Probability Sampling(1)(1)l Purposiveorjudgmentalsampling(立意抽样).Atypeofnonprobabilitysamplinginwhichyouselecttheu
42、nitstobeobservedonthebasisofyourownjudgmentaboutwhichoneswillbethemostusefulorreprsentative.3.3 Non-Probability Sampling(2)(2)l Quota sampling(配 额 抽 样).A type ofnon-probabilitysamplinginwhichunitsareselected into the sample on the basis ofprespecifiedcharacteristics,sothatthetotalsample will have th
43、e same distribution ofcharacteristicsasareassumedtoexistinthepopulationbeingstudied.3.3 Non-Probability Sampling(3)(3)l Snowballsampling(滚 雪 球 抽 样).Anon-probability sampling method oftenemployed in filed research.Each personinterviewed may be asked to suggestadditionalpeopleforinterviewing.3.4 Facto
44、rs influencing sample sizel A.populationsize 样本规模l B.populationheterogeneity 样本异质性l variance(方差)l C.permitedsamplingerror 允许抽样误差Chapter 4 Social Measurementl 4.1OperationalizationandSocialMeasurementl A.OperationalizationofResearchProject（研究课题的操作化）l B.SocialMeasurement（社会测量）4.2LevelsofSocialMeasurem
45、ent A.NominalMeasure（定类测量）B.OrdinalMeasure（定序测量）C.IntervalMeasure（定距测量）D.Ratiomeasure（定比测量）l 4.3.ReliabilityandValidityl A.Reliability（信度）l B.Validity（效度）l C.Relationsbetweenreliabilityandvalidity4.1 Operationalization and Social Measurementl A.OperationalizationofResearchProject a.Operationaldefini
46、tionofconceptl Operationaldefinitionadefinitionthatspellsoutpreciselyhowtheconceptwillbemeasured.Strictlyspeaking,anoperationaldefinitionisadescriptionofthe“operations”thatwillbeundertakeninmeasuringaconcept.b.Choiceofindexesl Example:Economicdevelopment-annualincomepercapita;collectiveincome Intell
47、igence-Couplerelation-c.Operationalizationofhypothesisl Concept:Industrialization-Humanrelationl Index:industrialoutput-timesvisitingeachotherl phonesubscribersB.Social Measurementl Conceptualizationl l Nominaldefinitionl l Operationaldefinitionlmeasurementsintherealworldl Definition:in order to und
48、erstand the nature,characteristics andconditionsoftheobjects,weallocatesomenumbersorsymbolstotheobjects according to some regulations.This process is called socialmeasurement.l Threeelementsofsocialmeasurement Objects Numberorsymbols regulations4.2 Levels of Social Measuremntl A.NominalMeasurel Vari
49、ableswhoseattributeshaveonlythecharacteristicsofexhaustivenessandmutualexclusivenessarenominalvariables.Examplesofthesewouldbesex,religiousaffiliation,politicalpartyaffiliation,birthplace,collegemajor,andhaircolor.l B.OrdinalMeasurel Variables whose attributes may be logically rank-ordered areordina
50、l measures.The different attributes represent relativelymoreorlessofthevariable.Variables of this type are social class,conservatism,alienation,prejudice,andthelike.c.Interval Measurel For the attributes composing some variables,theactual distance separating those attributes does havemeaning.Such va