《研究设计之测量》由会员分享，可在线阅读，更多相关《研究设计之测量（40页珍藏版）》请在金锄头文库上搜索。
1、研究设计之测量School of Public Administration & PolicyDr. Kaifeng YangIssuesl概念操作化概念化指标化l测量的层次l复合指数测量l测量的好坏：效度与信度l提高效度与信度的途径概念操作化沟通绩效沟通绩效?目标清晰度目标清晰度?例子沟通绩效沟通绩效?目标清晰度目标清晰度?从名义/概念定义到操作定义lNominal (Conceptual) DefinitionA definition that is simply assigned to a term without any claim that the definition repres
2、ents a “real” entity. It is A) defined by others; b) what it is vs. what it is not; c) shared; d) realistic and sensible. lOperational (Working) DefinitionSpecifies precisely how a concept will be measured菜谱菜谱概念化The process we specify what we mean when we use particular terms. It involves describing
3、 the essential features of the terms. Sometimes, it involves indicators well be using to measure our concept and the different aspects of the concept (dimensions). lIndicator(指标): a sign of the presence or absence of the conceptlDimension (纬度/变量): a specifiable aspect of a concept爱？爱？指标化: Political
4、AlienationConceptualizationDefining the conceptNominal Definition(Variables)Operational Definition(Indicators)InstrumentationPolitical distrust, powerlessness, and meaninglessnessPolitical Distrust: the general feeling that government isno longer of the people, by the people, and for the peopleIndic
5、ators are responses to the following questions:1.Do you think that quite a few of the people running the government are a little crooked, not very many are, or do you think that hardly any are crook at all?2.How much of the time do you think you can trustthe government to do what is right?3.Would yo
6、u say that the government is pretty much run by a few big interests looking out for themselvesor that it is run for the benefit of all people?General Social Survey, 2000, National Opinion ResearchTheoryabstractDataConcrete指标化：Other ExampleslLiteracy: The completion of six years of formal educationTh
7、ose nations in which at least 50 percent of the population has had six years of formal education, as indicated in a publication of the United NationslDemocracy:A system of government in which public officials are selected in competitive electionsThose countries in which the second-place finishers in
8、 elections for the chief executive office has received at least 25 percent of the vote at least once in the past eight yearsTo operationalize your concepts is arbitrary, but you have to make some justification if not based on common literature or policy.指标化：例子Social StatusEducationIncomeOccupationNu
9、mbers of school years completedCross family income last yearBlue collar, white collar, or professionalPoliticalParticipationVotingCampaign contributionAttend political rally“Did you vote in the last”“Did you contribute to ”“Have you attended a ”ConceptVariableOperational DefinitionIn the sample arti
10、cle?In the sample article? Communication PerformanceConceptualizationNominal Definition(Variables)Operational Definition(Indicators)InstrumentationExternal Communication Performancep.49Reverse: 从问题/数据到概念？l“How many times a week do you drink an alcoholic beverage?”1. None2. 12 3. 35 4. 57 5. 710 6. 1
11、0lPercentage of a nations population that is literatel“I often feel lonely” 1. agree 2. disagreel“number of hours of sleep each night”l“number of trips taken abroad each year by presidents”指标与概念的不完全契合概念指标指标2指标3指标5指标4指标指标1Level of Measurement1.“How many times a week do you drink an alcoholic beverage
12、?”1.1. None 2. 12 3. 35 4. 57 5. 710 6. 102.“How many times a week do you drink an alcoholic beverage?” _3.“Do you think you are addicted to alcohol? 1. Yes2. No4.“I am alcoholic.” 1. Strongly agree 2. Agree 3. Neutral 4. Disagree 5. Strongly DisagreePrecision/Level of MeasurementlNominal Measures（定
13、类）exhaustive and mutual exclusive categories; none is more or less than anotherlOrdinal Measures（定序）can logically rank-order: with more or less of particular attributelInterval Measures（定距）How much smaller or larger; the distance between each unit on the scale must be the same; lRatios Measures（定比）I
14、nterval measures; the zero point has a true meaning (absence of the characteristic being measured) Level of MeasurementLevel of Measurement选择测量层次l如果可能，选择定比/定距l受其他因素影响变量本身的特点敏感性（如收入）信度与效度PracticeslYou have data on the annual salary of 200 employees of an organization. How the data can be presented as
15、 ratio, interval, ordinal, and nominal data?复合指数测量：什么是？复合指数测量：为什么？概念指标指标2指标3指标5指标4指标指标1例子：怎么测量国家的“自由”程度？(Country)12345Privately owned newspapers10001Legal right to form political parties11000Contested elections for public offices11000Voting rights for most of the adults11010Limitations on government
16、s ability to incarcerate citizens10001Index score530121= Yes; 0=No.李克特量表lLikert Format (for other formats, refer to the textbook)SD1D2U3A4SA5Privately owned newspapersLegal right to form political partiesContested elections for public officesIndex score for Observation x15 or 15/3=5测量的好坏？How do you
17、measure individuals alcohol addiction?l “How many times a week do you drink an alcoholic beverage?”1.1. None 2. 12 3. 35 4. 57 5. 710 6. 10l“How many times a week do you drink an alcoholic beverage?” _l“Do you think you are addicted to alcohol? 1. Yes2. Nol“I am alcoholic.” 1. Strongly agree 2. Agre
18、e 3. Neutral 4. Disagree 5. Strongly DisagreelHow many bottles of alcohol do you normally drink for a week? _lHow many bottles of alcohol do you normally drink for a day?测量的准确度lTo what extent are you measuring what you intended to measure? lIdeal: Measurement error is 0Measurement = Intended charact
19、eristic + Systematic error + Random errorvSystematic error is durablevRandom error is temporaryPre-test = Math Ability + _+_ 准确度: 信度lReliability: produce same results over repeated applications. Stability and ConsistencyTest-Retest method 再测信度* Two times* maturation* sensitivityAlternative format复本信
20、度* two times*maturationSplit-Halves method (multiple measures, one concept)折半信度Sub-sample method 亚样本信度Split-HalvesMeasuring Performance measurement (PM) effectiveness1.Our PM information can be trusted2.Our PM helps managerial decisions3.Our PM improves communication between city hall and us4.Our PM
21、 help elected officials formulate budget5.Our PM indictors reflect our management effectiveness6.Our PM indictors are reliable7.Our investment in PM is worthwhile 8.Our PM improves productivity9.Our PM motivates employees10.Our PM helps adjusting strategic planning 准确度：效度lValidity: the extent to whi
22、ch an empirical measure adequately reflects the real meaning of the concept under consideration.Face validity表面效度: Does it appear? Judgment!Content validity内容效度: Got everything in?Consensual validity共识效度: Everybody agrees!Construct validityCriterion-related validity* Predictive validity * Concurrent
23、 validityInteritem associationDiscriminant validity测量误差与信度、效度Measurement = Intended characteristic + Systematic error + Random error Systematic error is durable, affecting validity Random error is temporary, affecting more on reliabilityWhich of the following questions concerns reliability?1.What do
24、es the Scholastic Aptitude Test (SAT) really measure?2. Do attitude scales really tap personal feelings or just what people think investigators want to hear?3. Is poverty best represented by measures of low absolute income (a minimum subsistence) or low relative income (e.g., 50% of national median
25、income)?4.How closely does self-reported church attendance correspond to actual church attendance?5.Are scores on the even-numbered and odd-numbered items on this test highly correlated?Research indicates that in recent years respondents answers to survey questions measuring racial prejudice underes
26、timate actual racial prejudice. This underestimate is an example of _ measurement error, which affects measurement _.lrandom; reliability lrandom; reliability and validity lsystematic; validitylsystematic; reliability and validitySystematic error would be least likely to occur with which of the foll
27、owing measures?1.a miscalibrated yardstick that is an inch short2.an IQ test developed for English-speaking U.S. citizens that is administered to French Canadians3.a question measuring child abuse that asks, “how often do you hit your child when she doesnt obey you?”4.scores on the multiple-choice p
28、ortion of an exam 5.reports of gambling winnings on IRS tax return Validity and Reliability Reliability is a necessary, but insufficient, condition, for validity validity is more important, but reliability is more easily tested Think about possible errors Low VLow RLow VHigh RLow VLow RHigh VHigh R提
29、高效度与信度：减少误差lParticipant (object who)lSituational factor (where, how, when)lMeasurer (subject who)lInstrument (what)lFacial attractiveness?提高效度与信度：减少误差lParticipant (object who)客体/对象lSituational factor (where, how, when)情境与程序lMeasurer (subject who)主体lInstrument (what)工具lFacial attractiveness?提高信度的途径l访谈、试测l增加同类问题/指标l去掉“区分性”较低的指标提高效度的途径l访谈、试测l去掉“区分性”较低的指标l多种测量方法SPSS学生设计的例子
