《信息系统研究行为学派讲课教案》由会员分享，可在线阅读，更多相关《信息系统研究行为学派讲课教案（44页珍藏版）》请在金锄头文库上搜索。
1、信息系统研究(ynji)的行为学派孙永强武汉大学(w hn d xu)信息管理学院1第一页，共44页。报告报告(bogo)(bogo)框框架架信息系统学科信息系统学科(xuk)简介简介信息系统行为学派信息系统行为学派(xupi)相关理论相关理论信息系统行为学派研究方法信息系统行为学派研究方法2第二页，共44页。学科学科(xuk)(xuk)简介简介3第三页，共44页。4Izak BenbasatRobert W. Zmud信息系统与信息科学(xn x k xu)的区别与联系？信信息息(x(xnxnx) )系系统统第四页，共44页。交叉学科属性交叉学科属性(shxng)(shxng)经济学经济学信
2、息系统信息系统计算机科计算机科学学工程学工程学管理科学管理科学市场市场(shch(shchng)ng)营营销学销学管理学管理学心理学与心理学与社会学社会学教育学教育学技术性范畴技术性范畴(fnchu)行为学范畴行为学范畴5第五页，共44页。6三大三大(sn d)(sn d)研究流派研究流派技术技术学派学派经济经济学派学派行为行为学派学派Izak BenbasatJay NunamakerA. B. Whinston第六页，共44页。7研究研究(ynji)(ynji)主题主题电子商务电子商务(din z shn w)(din z shn w)技术技术(jsh)(jsh)采纳采纳知识管理知识管理I
3、TIT战略战略人机交互人机交互移动商务移动商务电子医疗电子医疗社交媒体社交媒体信任信任隐私隐私技术抵制技术抵制技术扩展技术扩展技术压力技术压力知识共享知识共享知识整合知识整合项目管理项目管理创新创新生产力悖论生产力悖论ITIT能力能力吸收能力吸收能力敏捷性敏捷性治理治理推荐系统推荐系统电子口碑电子口碑媒体丰富度媒体丰富度交互性交互性第七页，共44页。8学术期刊学术期刊MIS QuarterlyInformation Systems ResearchJournal of Management Information SystemsJournal of the Association for In
4、formation SystemsEuropean Journal of Information SystemsInformation Systems JournalJournal of Information TechnologyJournal of Strategic Information SystemsSource：http:/ CountAdjusted CountCountry1Georgia State University (J Mack Robinson College of Business)6430.59USA2University of British Columbia
5、 (Sauder School of Business)3821Canada3University of Maryland (Robert H Smith School of Business)3618.52USA4University of London (London School of Economics and Political Science)2817.43UK5University of Texas at Austin (McCombs School of Business)3214.53USA6National University of Singapore (School o
6、f Computing) 2913.65Singapore7City University of Hong Kong (College of Business)3013.23China8Temple University (Fox School of Business and Management)2413.17USA9University of Arizona (Eller College of Management)3012.82USA10University of Arkansas (Sam M Walton College of Business)2411.45USAUniversit
7、y Ranking: Top 8 Journal, 2007-2011. Source： http:/ StraubArun RaiIzak BenbasatPaul PavlouAngelika DimokaRitu AgarwalBernard TanV. VenkateshJ. NunamakerHsinchun ChenPaulo GoesAndrew WhinstonDoug VogelK K Wei第九页，共44页。10学术期刊学术期刊交叉学科交叉学科管理科学管理科学管理学管理学营销学营销学DSSI&MIJHCSIEEE-TEMMSORPOMJOMAMJAMRASQSMJOSJCR
8、JMRJMJIBSMktSJASIST其他(qt)学科A类交叉(jioch)B类第十页，共44页。11学术期刊学术期刊UT Dallas Journal List （24）The Accounting ReviewMarketing ScienceJournal of Accounting and EconomicsManagement ScienceJournal of Accounting ResearchOperations ResearchJournal of FinanceJournal of Operations ManagementJournal of Financial Eco
9、nomicsManufacturing and Service Operations ManagementThe Review of Financial StudiesProduction and Operations ManagementInformation Systems ResearchAcademy of Management JournalJournal of ComputingAcademy of Management ReviewMIS QuarterlyAdministrative Science QuarterlyJournal of Consumer ResearchOr
10、ganization ScienceJournal of MarketingJournal of International Business StudiesJournal of Marketing ResearchStrategic Management JournalSource： http:/jindal.utdallas.edu/the-utd-top-100-business-school-research-rankings/list-of-journals/第十一页，共44页。12学术会议学术会议ICIS (每年每年5月初截稿月初截稿(ji o)，12月中月中开会）开会）ECIS
11、(每年每年12月初截稿月初截稿(ji o)，次，次年年6月中开会）月中开会）AMCIS (每年每年3月月初初(yuch)截稿，截稿，8月月中开会）中开会）PACIS (每每年年3月初截月初截稿，稿，7月中月中开会）开会）HICSS (每每年年6月中截月中截稿，次年稿，次年1月中开会）月中开会）第十二页，共44页。13学术学术(xush)(xush)组织组织Doug VogelAssociation for Information SystemsSource: http:/start.aisnet.org/K. K. WeiChairFellowsT. P. LiangB. C. Y. Tan第
12、十三页，共44页。理理 论论14第十四页，共44页。什么什么(shn me)(shn me)是理论？是理论？15第十五页，共44页。K. R. Popper理论理论(lln)(lln)的的定义定义P1TSEEP2Falsifiability证伪原则(yunz)PropositionTentativeSolutionErrorEliminationIsaac NewtonAlbert Einstein16第十六页，共44页。理论理论(lln)(lln)的的定义定义ConceptsRelationships+WhatHowWhyWhen17第十七页，共44页。常见理论常见理论(lln)(lln)关
13、系关系IndependentVariableDependentVariableMain EffectDirect Effect18第十八页，共44页。常见理论常见理论(lln)(lln)关系关系IndependentVariableDependentVariableBlack BoxMediating EffectMediatorIndirect Effect19第十九页，共44页。常见常见(chn (chn jin)jin)理论关系理论关系IndependentVariableDependentVariableBoundaryScopeModerating EffectModeratorIn
14、teraction Effect20第二十页，共44页。常见常见(chn (chn jin)jin)理论关系理论关系IVDVInverted-U Effect21第二十一页，共44页。常见常见(chn (chn jin)jin)理论关系理论关系ModeratedMediating22第二十二页，共44页。常见理论常见理论(lln)(lln)关系关系Mediated Moderating23第二十三页，共44页。常见常见(chn (chn jin)jin)理论关系理论关系ModeratedInverted-UInverted-U EffectIVDVLowHigh24第二十四页，共44页。常见理
15、论常见理论(lln)(lln)关系关系Inverted-UModeratingInverted-UIVDV中低高25第二十五页，共44页。理论理论(lln)(lln)基基础础Theories Used in IS Researchhttp:/istheory.byu.edu/wiki/Main_PageTRATPBTTFIS SuccessSocial CapitalSocial IdentitySocial Exchange26第二十六页，共44页。方方 法法27第二十七页，共44页。命题命题(mng t)(mng t)与假设与假设Conceptual LevelOperational Le
16、velConstructsPropositionsVariablesHypotheses28第二十八页，共44页。数据数据(shj)(shj)收收集集ExperimentSurveyInterviewSecondary DataObservation29第二十九页，共44页。1st和和2nd 统计统计(tngj)技术技术1G (Multivariate regression)2G (Structural equation modeling, SEM)Dependent variables (DV) Single DV Multiple DVsMeasurement model Separate
17、 Simultaneous with structuralStructural model Separate SystematicRepresentative software SPSS PLS, LISRELIV1DV2DV1IV1DV1IV1DV2DV1IV1DV2 Test the measurement model first Pack items into variable (e.g., mean)30第三十页，共44页。潜在与观测潜在与观测(gunc)变量变量Reputation of WHUs SIMRISC1: Highly rated by iSchools.RISC2: L
18、isted as one of the best IM school.RISC3: Recommended by scholars.LatentVariableObservableVariableCannot be directly observedCan be directly observed31第三十一页，共44页。反射与组成反射与组成(z chn)测量测量(Petter et al. 2007)ReflectiveFormativeCausal directionLatent ObservableObservable LatentInterchangeabilityYesNoCo-va
19、rySuggestedNot suggestedReputation of WHUs SIMReputation of WHUHighly RatedListed in bestRecom.SIMRepu.EMSRepu.It is an issue of how to measure it rather than what the construct should be. 32第三十二页，共44页。一阶与二阶变量一阶与二阶变量(binling)Reputation of WHUSIM Repu.EMSRepu.Second-order constructFirst-order constru
20、ctItems Second-order construct as a strategy for balancing simplicity and comprehensiveness. The relationship between first- and second-order constructs can be reflective or formative. Selection between first- and second-order construct: abstraction level and research objective (e.g., social capital
21、). 33第三十三页，共44页。测量测量(cling)与结与结构模型构模型IVDVMeasurement ModelMeasurement ModelStructural ModelMeasurement ModelStructural ModelRelationships Latent - observable Latent - LatentTesting issues Reliability Convergent validity Discriminant validity Path coefficients R-square Fit index34第三十四页，共44页。探索性与验证探索性
22、与验证(ynzhng)性因子分析性因子分析V1V2V1V2Unknown, unspecified BlackboxEFACFALatent-observable relationshipUnspecifiedSpecifiedSoftwareSPSSPLS, LISREL35第三十五页，共44页。基于方差与协方差的基于方差与协方差的结构结构(jigu)方程方程模型模型Model StructureMatchIVDVData StructurePLS-SEM (Partial Least Squares): Pursue the max. R-square explained. Make th
23、e DV more predictable.CB-SEM (Covariance-based): Pursue the match between data and model. Make the model more reliable.36第三十六页，共44页。工具选择工具选择(xunz)标准标准Reasons for using PLS-SEMReasons for using CB-SEM Exploratory study Confirmatory study Small sample Large sample (CB-SEM assumption) Formative measure
24、s Reflective measures Formative measures with two emitting paths (specification issues). Abnormal distribution Normal distribution (CB-SEM assumption) Need to use latent variable scores Require a global goodness-of-fit If CB-SEM is applicable, taking CB-SEM as the priority (exploratory confirmatory
25、goal is questionable) more rigor in algorithm. PLS-SEM can be a good approximation of CB-SEM even when the study is confirmatory in nature (strong theoretical foundation) A silver bullet.37第三十七页，共44页。报告报告(bogo)结构结构PLS-SEMCB-SEMMeasurement ModelReliability Cronbachs alpha Composite reliability (CR) A
26、verage variance extracted (AVE) Cronbachs alpha Composite reliability (CR) Average variance extracted (AVE)Convergent validity Loadings Errors T-statistics of loadings Loadings Errors T-statistics of loadingsDiscriminant validity Cross loadings Correlations and square root of AVE Correlations and sq
27、uare root of AVE Chi-square change of nested modelsStructural Model Path coefficients, t-value R-square Path coefficients, t-value R-square Fit index38第三十八页，共44页。软件软件(run jin)与与统计量统计量SoftwareOperationStatisticsSPSS Descriptive statistics Descriptive (e.g., mean, sd), frequency Scale Cronbachs alpha
28、EFA Loadings and cross-loadings Correlation Correlations Regression Path coefficient, t-value, p-valuePLS-SEM(e.g., SmartPLS) PLS algorithm Cronbachs alpha, composite reliability, AVE Loading, cross loading Correlation R-square Bootstrapping Loadings, path coefficients and their t-statisticsCB-SEM(e
29、.g., LISREL) Graph Loadings, path coefficients, errors, R-square, t-value (CR, AVE should be calculated) Chi-square, df, RMSEA Text Correlations Fit index (e.g., CFI, NFI, GFI, AGFI, etc.)39第三十九页，共44页。中介中介(zhngji)作作用分析用分析IVDVMeBaron & Kenny (1986)Step 1: IVDV (Sig.)Step 2: IVMe (Sig.)Step 3: (IV, Me
30、)DVIf IVDV (Sig), MeDV (NS): No mediating.If IVDV (Sig), MeDV (Sig.): PartialIf IVDV (NS), MeDV (Sig.): FullSobels Z test: (IVMe) * (Me DV) 0Zhao et al. (2010): Step 1 is not needed; multiple opposite mediators. 40第四十页，共44页。调节作用分析调节作用分析(fnx)IVDVMoContinuous Variables (Chin 2003)Step 1: Standardize v
31、ariables.Step 2: Interaction component IVM=IV*Mo Step 3: (IV, Mo)DV Step 4: (IV, Mo, IVM)DV If IVMDV (Sig.), moderating support. Check R-square change between step 3 and 4.Category Variables (Keil et al. 2002) Step 1: Run data using different sub-samples.Step 1: Compare the path coefficients for the
32、 same path.41第四十一页，共44页。倒倒U型作用型作用(zuyng)分析分析IVDVy=b0+a1*x2+a2*x+eTest a1042第四十二页，共44页。结语结语(jiy)You may truly understand only when using it!Systematically learn the fundamental and heuristically learn the required!No perfect, only appropriate!Analysis is not driven by data but built on theory!Excellent method brings B to A, bad method takes A to B!43第四十三页，共44页。Stay Hungry, Stay Foolish！44第四十四页，共44页。
