- 1、本文档共41页,可阅读全部内容。
- 2、原创力文档(book118)网站文档一经付费(服务费),不意味着购买了该文档的版权,仅供个人/单位学习、研究之用,不得用于商业用途,未经授权,严禁复制、发行、汇编、翻译或者网络传播等,侵权必究。
- 3、本站所有内容均由合作方或网友上传,本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺!文档内容仅供研究参考,付费前请自行鉴别。如您付费,意味着您自己接受本站规则且自行承担风险,本站不退款、不进行额外附加服务;查看《如何避免下载的几个坑》。如果您已付费下载过本站文档,您可以点击 这里二次下载。
- 4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等,请点击“版权申诉”(推荐),也可以打举报电话:400-050-0827(电话支持时间:9:00-18:30)。
TheSimpleRegressionModel y=b0+b1x+u1
SomeTerminologyInthesimplelinearregressionmodel,wherey=b0+b1x+u,wetypicallyrefertoyastheDependentVariable,orLeft-HandSideVariable,orExplainedVariable,orRegressand2
SomeTerminology,cont.Inthesimplelinearregressionofyonx,wetypicallyrefertoxastheIndependentVariable,orRight-HandSideVariable,orExplanatoryVariable,orRegressor,orCovariate,orControlVariables3
ASimpleAssumptionTheaveragevalueofu,theerrorterm,inthepopulationis0.Thatis,E(u)=0Thisisnotarestrictiveassumption,sincewecanalwaysuseb0tonormalizeE(u)to04
ZeroConditionalMeanWeneedtomakeacrucialassumptionabouthowuandxarerelatedWewantittobethecasethatknowingsomethingaboutxdoesnotgiveusanyinformationaboutu,sothattheyarecompletelyunrelated.Thatis,thatE(u|x)=E(u)=0,whichimpliesE(y|x)=b0+b1x5
..x1x2E(y|x)asalinearfunctionofx,whereforanyxthedistributionofyiscenteredaboutE(y|x)E(y|x)=b0+b1xyf(y)6
OrdinaryLeastSquaresBasicideaofregressionistoestimatethepopulationparametersfromasampleLet{(xi,yi):i=1,…,n}denotearandomsampleofsizenfromthepopulationForeachobservationinthissample,itwillbethecasethatyi=b0+b1xi+ui7
....y4y1y2y3x1x2x3x4}}{{u1u2u3u4xyPopulationregressionline,sampledatapointsandtheassociatederrortermsE(y|x)=b0+b1x8
DerivingOLSEstimatesToderivetheOLSestimatesweneedtorealizethatourmainassumptionofE(u|x)=E(u)=0alsoimpliesthatCov(x,u)=E(xu)=0Why?RememberfrombasicprobabilitythatCov(X,Y)=E(XY)–E(X)E(Y)9
DerivingOLScontinuedWecanwriteour2restrictionsjustintermsofx,y,b0andb1,sinceu=y–b0–b1xE(y–b0–b1x)=0E[x(y–b0–b1x)]=0Thesearecalledmomentrestrictions10
DerivingOLSusingM.O.M.Themethodofmomentsapproachtoestimationimpliesimposingthepopulationmomentrestri
文档评论(0)