计量经济学英文重点知识点考试必备.docx

计量经济学英文重点知识点考试必备.docx

《计量经济学英文重点知识点考试必备.docx》由会员分享，可在线阅读，更多相关《计量经济学英文重点知识点考试必备.docx（32页珍藏版）》请在冰豆网上搜索。

计量经济学英文重点知识点考试必备计量经济学英文重点知识点考试必备第一章1.Econometrics（计量经济学）：

thesocialscienceinwhichthetoolsofeconomictheory,mathematics,andstatisticalinferenceareappliedtotheanalysisofeconomicphenomena.theresultofacertainoutlookontheroleofeconomics,consistsoftheapplicationofmathematicalstatisticstoeconomicdatatolendempiricalsupporttothemodelsconstructedbymathematicaleconomicsandtoobtainnumericalresults.2.Econometricanalysisproceedsalongthefollowinglines计量经济学分析步骤1）Creatingastatementoftheoryorhypothesis.建立一个理论假说2）Collectingdata.收集数据3）Specifyingthemathematicalmodeloftheory.设定数学模型4）Specifyingthestatistical,oreconometric,modeloftheory.设立统计或经济计量模型5）Estimatingtheparametersofthechoseneconometricmodel.估计经济计量模型参数6）Checkingformodeladequacy:

Modelspecificationtesting.核查模型的适用性：

模型设定检验7）Testingthehypothesisderivedfromthemodel.检验自模型的假设8）Usingthemodelforpredictionorforecasting.利用模型进行预测Step2：

收集数据Threetypesofdata三类可用于分析的数据1）Timeseries（时间序列数据）:

Collectedoveraperiodoftime,arecollectedatregularintervals.按时间跨度收集得到2）Cross-sectional截面数据:

Collectedoveraperiodoftime,arecollectedatregularintervals.按时间跨度收集得到3）Pooleddata合并数据（上两种的结合）Step3：

设定数学模型1.plotscatterdiagramorscattergram2.writethemathematicalmodelStep4：

设立统计或经济计量模型CLFPRisdependentvariable应变量CUNRisindependentorexplanatoryvariable独立或解释变量（自变量）WegiveacatchallvariableUtostandforalltheseneglectedfactorsInlinearregressionanalysisourprimaryobjectiveistoexplainthebehaviorofthedependentvariableinrelationtothebehaviorofoneormoreothervariables,allowingforthedatathattherelationshipbetweenthemisinexact.线性回归分析的主要目标就是解释一个变量（应变量）与其他一个或多个变量（自变量）只见的行为关系，当然这种关系并非完全正确Step5：

估计经济计量模型参数Inshort,theestimatedregressionlinegivestherelationshipbetweenaverageCLFPRandCUNR简言之，估计的回归直线给出了平均应变量和自变量之间的关系Thatis,onaverage,howthedependentvariablerespondstoaunitchangeintheindependentvariable.单位因变量的变化引起的自变量平均变化量的多少。

Step6：

核查模型的适用性：

模型设定检验Thepurposeofdevelopinganeconometricmodelisnottocapturetotalreality,butjustitssalientfeatures.Step7：

检验自模型的假设WhydoweperformhypothesistestingWewanttofindourwhethertheestimatedmodelmakeseconomicsenseandwhethertheresultsobtainsconformwiththeunderlyingeconomictheory.第二章1.Themeaningofregression（回归）Regressionanalysisisconcernedwiththestudyoftherelationshipbetweenonevariablecalledthedependentorexplainedvariable,andoneormoreothervariablescalledindependentorexplanatoryvariables.2.Objectivesofregression1）Estimatethemean,oraverage,andthedependentvaluesgiventheindependentvalues2）Testhypothesesaboutthenatureofthedependence-hypothesessuggestedbytheunderlyingeconomictheory3）Predictorforecastthemeanvalueofthedependentvariablegiventhevaluesoftheindependents4）Oneormoreoftheprecedingobjectivescombined3.PopulationRegressionLine（PRL）Inshort,thePRLtellsushowthemean,oraverage,valueofYisrelatedtoeachvalueofXinthewholepopulation4.ThedependenceofYonX,technicallycalledtheregressionofYonX.5.HowdoweexplainitAstudentsscore,say,theithindividual,correspondingtoaspecificfamilyincomecanbeexpressedasthesumoftwocomponents1）Thecomponentcanbecalledthesystematic,ordeterministic,component.2）Maybecalledthenonsystematicorrandomcomponent6.WhatisthenatureofU（stochasticerror）term1）Theerrortermmayrepresenttheinfluenceofthosevariablesthatarenotexplicitlyincludedinthemodel.误差项代表了未纳入模型变量的影响2）Someintrinsicrandomnessinthemathscoreisboundtooccurthatcannotbeexplainedevenweincludeallrelevantvariables.即使模型包括了决定性数学分数的所有变量，内在随机性也不可避免，这是做任何努力都无法解释的。

3）Umayalsorepresenterrorsofmeasurement.U还代表了度量误差4）TheprincipleofOckhamsrazor-thedescriptionbekeptassimpleaspossibleuntilprovedinadequate-wouldsuggestthatwekeepourregressionmodelassimpleaspossible.“奥卡姆剃刀原则”，描述应该尽可能简单，只要不遗漏重要信息。

这表明回归模型应尽可能简单。

7.HowdoweestimatethePRF（populationregressionfunction）Unfortunately,inpractice,Werarelyhavetheentirepopulationinourdisposal,oftenwehaveonlyasamplefromthispopulation.8.GrantedthattheSRFisonlyanapproximationofPRF.CanwefindamethodoraprocedurethatwillmakethisapproximationascloseaspossibleSRF仅仅是PRF的近似，那么能不能找到一种方法使这种近似尽可能接近真实呢9.Specialmeaningof“linear”1）Linearityinthevariables变量线性Theconditionalmeanvalueofthedependentvariableisalinearfunctionoftheindependentvariables2）LinearityintheParameters参数线性Theconditionalmeanofthedependentvariableisalinearfunctionoftheparameters,theBs;itmayormaynotbelinearinthevariables.第三章1.UnlesswearewillingtoassumehowthestochasticUtermsaregenerated,wewillnotbeabletotellhowgoodanSRFisasanestimateofthetruePRF.只有假定了随机误差的生成过程，才能判定SRF对PRF拟合的是好是坏。

2.ClassicalLinearRegressionModel1）Assumption1:

Theregressionmodelislinearintheparameters.Itmayormaynotbelinearinthevariables.回归模型是参数线性的，但不一定是变量线性的。

2）Assumption2:

TheexplanatoryvariablesXisuncorrelatedwiththedisturbancetermU.Xsarenonstochastic,Uisstochastic.解释变量X与扰动误差项u不相关.X是非随机的，U是随机的。

3）Assumption3:

GiventhevalueofXi,theexpected,ormeanvalueofthedisturbancetermUiszero.给定Xi，扰动项的期望或均值为零。

DisturbanceUrepresentallthosefactorsthatarenotspecificallyintroducedinthemodel干扰项U代表了所有未纳入模型的影响因素。

4）Assumption4:

ThevarianceofeachUiisconstant,orhomoscedastic.U的方差为常数，或同方差。

Homoscedasticity（同方差）:

a.ThisassumptionsimplymeansthattheconditionaldistributionofeachYpopulationcorrespondingtothegivenvalueofXhasthesamevariance.该假定表明，与给定的X相对应的每个Y的条件分布具有同方差。

b.TheindividualYvaluesarespreadaroundtheirmeanvalueswiththesamevariance.即每个Y值以相同的方差分布在其均值周围。

5）Assumption5:

Thereisnocorrelationbetweentwoerrorterms,thisistheassumptionofno-autocorrelation.无自相关假定，即两个误差项之间不相关。

6）Assumption6:

Theregressionmodeliscorrectlyspecified.回归模型是正确假定的。

Thereisnospecificationbiasorspecificationerrorinthemodel.实证分析的模型不存在设定偏差或设定误差。

Thisassumptioncanbeexplainedinformallyasfollows.Aneconometricinvestigationbeginswiththespecificationoftheeconometricmodelunderlyingthephenomenonofinterest.andStandarderrorsofOLSestimators普通最小二乘估计量的方差与标准误:

OneimmediateresultoftheassumptionsintroducedisthattheyenableustoestimatethevariancesandstandarderrorsoftheOLSestimatorsgiveninEq.and.shouldknow:

VariancesoftheestimatorsStandarderrorsoftheestimatorsisthevalueofThehomoscedasticisestimatedfromformulaErroroftheRegression（SER）回归标准误IssimplythestandarddeviationoftheYvaluesabouttheestimatedregressionline.Y值偏离估计回归的标准差。

ofmathfunction1）InterpretationThestandarddeviation,orstandarderror,is,isameasureofvariabilityofb2fromsampletosample.Ifwecansaythatourcomputedb2lieswithinacertainnumberofstandarddeviationunitsfromthetrueB2,wecanstatewithsomeconfidencehowgoodthecomputedSRFisasanestimatorofthetruePRF.2）SamplingDistribution抽样分布Oncewedeterminethesamplingdistributionofourtwoestimators,thetaskofhypothesistestingbecomesstraightforward.一旦确定了两个估计量的抽样分布，那么假设检验就是举手之劳的事情。

doweuseOLSThepropertiesofOLSestimatorsThemethodofOLSisusedpopularlynotonlybecauseitiseasytousebutalsobecauseithassomestrongtheoreticalproperties.OLS法得到广泛使用，不仅是因为它简单易行，还因为它具有很强的理论性质。

theorem高斯-马尔科夫定理Giventheassumptionsoftheclassicallinearregressionmodel（CLRM）,theOLSestimatorshaveminimumvarianceintheclassoflinearOLSestimatorsareBLUE（bestlinearunbiasedestimators）满足古典线性模型的基本假定，则在所有线性据计量中，OLS估计两具有最小方差性，即OLS是最优线性无偏估计量（BLUE）10.BLUEproperty最优线性无偏估计量的性质1）B1andB2arelinearestimators.B1和B2是线性估计量2）Theyareunbiased,thatisE（b1）=B1,E（b2）=B2.B1和B2是无偏估计两3）TheOLSestimatoroftheerrorvarianceisunbiased.误差方差的OLS估计量是无偏的4）b1andb2areefficient和B2是有效估计量Var（b1）islessthanthevarianceofanyotherlinearunbiasedestimatorofB1Var（b2）islessthanthevarianceofanyotherlinearunbiasedestimatorofB211.MonteCarlosimulation蒙特卡洛模拟DotheexperimentatlabDoitbyExcell.=NORMINV（RAND（）,0,2）Doitbymatlab.=NORMINV（uniform（）,MU,SIGMA）DoitbyStata.=invnorm（uniform（）12.CentralLimitTheorems中心极限定理Ifthereisalargenumberofindependentandidenticallydistributed（iid）randomvariables,then,withafewexceptions,thedistributionoftheirsumtendstobeanormaldistributionasthenumberofsuchvariablesincreasesindefinitely.随着变量个数的无限增加，独立同分布随机变量近似服从正态分布13.RecallU,theerrortermrepresentstheinfluenceofallthoseforcesthataffectYbutarenotspecificallyincludedintheregressionmodelbecausetherearesomanyofthemandtheindividualeffectofanyonesuchforceonYmaybetoominor.误差项代表了未纳入回归模型的其他所有因素的影响。

因为在这些影响中，每种因素对Y的影响都很微弱Ifalltheseforcesarerandom,ifweletUrepresentthesumofalltheseforces,thenbyinvokingtheCLT,wecanassumethattheerrortermUfollowsthenormaldistribution.如果所有这些影响因素都是随机的，用U代表所有这些影响因素之和，那么根据中心极限定理，可以假定误差项服从正态分布。

14.Anotherpropertyofnormaldistribution另一个正态分布的性质Anylinearfunctionofanormallydistributedvariableisitselfnormallydistributed.正态变量的性质函数仍服从正态分布。

15.Hypothesistesting假设检验HavingknownthedistributionofOLSestimatorsb1andb2,wecanproceedthetopicofhypothesistesting.16.Nullhypothesis零假设“zero”nullhypothesisisdeliberatelychosentofindoutwhetherYisrelatedtoXalall,whichisalsocalledstrawmanhypothesis.之所以选择这样一个假设是为了确定Y是否与X有关，也称为稻草人假设。

17.Weneedsomeformaltestingproceduretorejectorreceivethenullhypothesisandmaketheskepticalguysshutup.需要正规的检验过程拒绝或接受零假设18.IfournullhypothesisisB2=0andthecomputedb2=,wecanfindouttheprobabilityof