版权说明:本文档由用户提供并上传,收益归属内容提供方,若内容存在侵权,请进行举报或认领
文档简介
EViews6.0beta在面板数据模型估计中的应用
来自免费的minixi1、进入工作目录cdd:\nklx3,在指定的路径下工作是一个良好的习惯2、建立面板数据工作文件workfile(1)最好不要选择EViews默认的blanacedpanel类型Moren_panel(2)按照要求建立简单的满足时期周期和长度要求的时期型工作文件
3、建立pool对象(1)新建对象2)选择新建对象类型并命名(3)为新建pool对象设置截面单元的表示名称,在此提示下(CrossSectionIdentifiers:(Enteridentifiersbelowthisline)输入截面单元名称。,建议采用汉语拼音,例如29个省市区的汉语拼音,建议在拼音名前加一个下划线“_”,如图
关闭建立的pool对象,它就出现在当前工作文件中。4、在pool对象中建立面板数据序列双击pool对象,打开pool对象窗口,在菜单view的下拉项中选择spreedsheet(展开表)在打开的序列列表窗口中输入你要建立的序列名称,如果是面板数据序列必须在序列名后添加“?”例如,输入GDP?,在GDP后的?的作用是各个截面单元的占位符,生成了29个省市区的GDP的序列名,即GDP后接截面单元名,再在接时期,就表示出面板数据的3维数据结构(1变量2截面单元3时期)了。请看工作文件窗口中的序列名。展开表(类似excel)中等待你输入、贴入数据。5、贴入数据(1)打开编辑(edit)窗口2)贴入数据(3)关闭pool窗口,赶快存盘见好就收6、在pool窗口对各个序列进行单位根检验选择单位根检验设置单位根检验
单位根检验结果单位根检验结果PoolUnitRootTestonK?Poolunitroottest:SummarySeries:K_BEIJING,K_TIANJIN,K_HEBEI,K_SHANXI_D,K_NEIMENG,K_LiAONING,KjjiLIN,K_HLJIANG,K_SHANGHAI,K.JIANGSU,K_ZHEJIANG,K_ANHUI,KFUJIAN,K_JIANGXI,K_SHANDONG,K_HENAN,K_HUBEI,K_HUNAN,K_GUANGDONG,K_GUANGXI,K~HAINAN,fCsiCHUArTK_GUIZHOU,K_YUNNAN,jCsHANX^X,K^GANSU,K^QINGHAI,kJnINGXIA,K_XINJIANG--Date:05/24/07Time:19:57--Sample:19862005Exogenousvariables:IndividualeffectsAutomaticselectionofmaximumlagsAutomaticselectionoflagsbasedonSIC:0to4Newey-WestbandwidthselectionusingBartlettkernelMethodStatisticProb.**CrosssectionsObsNull:Unitroot(assumescommonunitrootprocess)Levin,Lin&Chu忙-2.660530.003929526Null:Unitroot(assumesindividualunitrootprocess)Im,PesaranandShinW-stat4.267011.000029526ADF-FisherChi-square19.30851.000029526PP-FisherChi-square14.51641.000029551**ProbabilitiesforFishertestsarecomputedusinganasymptoticChi-squaredistribution.Allothertestsassumeasymptoticnormality.注意检验方法和两种检验的零假设:Null:Unitroot(assumescommonunitrootprocess)各截面有相同的单位根Null:Unitroot(assumesindividualunitrootprocess)允许各截面有不同单位根
其中,Levin,Lin&Chut*检验拒绝含有单位根的零假设,即拒绝非平稳7、在pool窗口对面板数据组合进行协整检验选择进行协整检验-!□!x|羁Pool:F4ZHANM(»aWorkfile:SHSH02:-!□!x|0.融IProc|Object|Print|Name|Freeze|Edit+/-1Order+/-1Smpl+/-1Format|Title|Estimate|Define|PoolGenr|SCrossSectionIdentifiersRepresentationsEstimationOutputResidualsCoefCovarianceMatrixCoefficientTests►Fixed/RandomEffectsTesting►Spreadsheet(stackeddata)...DescriptiveStatistics..UnitRootTest...CointegrationTest...LabelBEIJING/998BEIJING-199?RepresentationsEstimationOutputResidualsCoefCovarianceMatrixCoefficientTests►Fixed/RandomEffectsTesting►Spreadsheet(stackeddata)...DescriptiveStatistics..UnitRootTest...CointegrationTest...LabelBEIJING/998BEIJING-199?BEIJING-2000BEIJING-20017.598307.G72G877.796413LNK?5.0006765.2814235.4350215.6846395.7038895.7148755.9679886.3524606.7073697.0477066.9501427.0506947.1768527.2620737.249070LNDH?8.1583398.3201558.3888588.4576498.5389738.6090248.6426188.6473678.7000828.7005228.7032898.7185908.6765078.6882858.703053LNXH?2.00568H2.02725!^2.04838:2.06907I2.08933I2.10920:2.128682.14778'2.16653-2.18493'2.20300'2.22075I2.2381912.25533'2.27248、协整检验设置对话框,注意有3种检验方法(testtype)协整检验结果,同样要注意两种假定(含有AR,即含有单位根,非协整),两种零假设都是非协整,小概率事件发生拒绝非协整。本例题检验的4个序列时协整的,特别提示还要看各个序列的单位根检验是否是同阶单整的,否则单凭协整检验的结果根据不足。
PedroniResidualCointegrationTestSeries:LNY?LNK?LNDH?LNXH?Date:05/24/07Time:20:14Sample:19862005Includedobservations:20Cross-sectionsineluded:29NullHypothesis:NocointegrationTrendassumption:NodeterministictrendLagselection:fixedat1Newey-WestbandwidthselectionwithBartlettkernelGrouprho-StatisticGroupPP-StatisticGrouprho-StatisticGroupPP-StatisticGroupADF-StatisticStatisticProb.3.8269590.00030.1998720.3911-3.6546000.0005Altemativehypothesis:commonARcoefs.(within-dimension)WeightedStatisticProb.StatisticProb.Panelv-Statistic1.4150600.14661.5389000.1221Panelrho-Statistic1.8843370.06761.6258930.1064PanelPP-Statistic0.0473930.3985-0.3684740.3728PanelADF-Statistic-3.2473110.0020-3.2811550.0018Alternativehypothesis:individualARcoefs.(between-dimension)CrosssectionspecificresultsPhillips-Peronresults(non-parametric)CrossIDAR(1)VarianceHACBandwidthObs8、建立混合模型在pool对象窗口的proc(过程)的下拉式菜单中选择估计打开模型设置窗口
混合模型的设置混合模型的结果D即endentVariable:LNY?Method:PooledLeastSquaresDate:05/24/07Time:20:30Sample:19862005Includedobservations:20Cross-sectionsincluded:29Totalpool(balanced)observations:580VariableCoefficientStd.Errort-StatisticProb.C-0.8602430.121396-7.0862770.0000LNK?0.8291890.01305963.495910.0000LNDH?0.2613960.01200521.773960.0000LNXH?0.2377270.0556284.2734790.0000LNNE1?-0.1452770.063819-2.2763740.0232LNCE1?0.0901580.0561431.6058730.1089R-squared0.986459Meandependentvar7.086138AdjustedR-squared0.986341S.D.dependentvar1.240231Fnfronro^Qinnn1AAQA7infnrrit&rinn-1nidRnq9、建立变系数模型这里只建立一次变一个变量且在截面维的变系数模型。当然也可是在时间维的变系数。而且可以一次不止变一个变量的系数。变系数模型的设置
变系数模型的估计结果DependentVariable:LNY?Method:PooledLeastSquaresDate:05/24/07Time:20:37Sample:19862005Includedobservations:20Cross-sectionsincluded:29Totalpool(balanced)observations:580VariableCoefficientStd.Errort-StatisticProb.C-1.0909600.215765-5.0562320.0000LNDH?0.3031280.02609311.617090.0000LNXH?0.1917570.1201801.5955750.1112LNNE1?-0.2482310.075168-3.3023300.0010LNCE1?0.6448430.0814977.9124580.0000BEIJING-LNKBEIJING0.7414960.02224433.334790.0000TIANJIN-LNKTIANJIN0.7727700.02240234.496290.0000HEBEI-LNKHEBEI0.7493170.01875839.947250.0000SHANXI_D-LNKSHANXI_D0.7416180.02142234.619030.0000NEIMENG-LNKNEIMENG0.7436640.02129534.921500.0000LIAONING-LNKLIAONING0.7869310.01974639.852630.0000JILIN-LNKJILIN0.7658240.02165935.358240.0000HLJIANG-LNKHLJIANG0.7833390.02071837.808940.0000
10、建立截距维的固定效应模型,并检验模型的冗余性(是否比混合模型优?)截面维固定效应模型的设置截面维固定效应模型的估计结果D即endentVariable:LNY?Method:PooledLeastSquaresDate:05/24/07Time:20:42Sample:19862005Includedobservations:20Cross-sectionsincluded:29Totalpool(balanced)observations:580VariableCoefficientStd.Errort-StatisticProb.C-0.7852040.267649-2.9337080.0035LNK?0.6907670.02006434.427310.0000LNDH?0.1038980.0385402.6958280.0072LNXH?1.3497620.1780527.5807240.0000LNNE1?-0.1652170.072697-2.2726610.0234LNCE1?0.3528760.0828214.2606880.0000FixedEffects(Cross)BEIJING-C-0.614424TIANJIN-C-0.436907HEBEI-C0.113717SHANXI_D-C-0.207641NEIMENG-C-0.209332LIAONING-C0.095655截面维固定效应模型的冗余性检验,首先在pool模型的view中选择似然比的检验菜单选项□Pool:FAZHANMOXIWorkfile:SHSH02::yongxufazhanmoxi\-|n|x|Mie\v!Proc|Object|Print|Name|FreezeEstimate|Define|PoolGenr|SheetCrossSectionIdentifiers▲RepresentationsEstimationOutputResiduals匚oef匚ovarianceMatrix匚oefficientTests0.267649-2.9337080.00350.02006434.427310.00000.0385402.6958280.00720.1780527.5807240.00000.072697-2.2726610.02340.0828214.2606880.0000RedundantFixedEffects-LikelihoodRatioCorrelatedRandomEffectsRedundantFixedEffects-LikelihoodRatioCorrelatedRandomEffects-HausmanTestJ4379832-0.1652170.352876Spreadsheet(stackeddata)...DescriptiveStatistics..UnitRootTest...CointegrationTest...LabelLNNE1?LNCE1?FiveriFffert*;fUrcM/似然比检验的结果,零假设固定效应模型是冗余的,小概率事件发生,拒绝冗余,于是摒弃混合模型:RedundantFixedEffectsTestsPool:FAZHANMOXITestcross-sectionfixedeffectsEffectsTestStatisticd.f.Prob.Cross-sectionF18.205856(28,546)0.0000Cross-sectionChi-square382.452544280.0000Cross-sectionfixedeffectstestequation:D即endentVariable:LNY?Method:PanelLeastSquaresDate:05/24/07Time:20:47Sample:19862005Includedobservations:20Cross-sectionsincluded:29Totalpool(balanced)observations:580CoefficientStd.Errort-StatisticProb.C-0.8602430.121396-7.0862770.0000LNK?0.8291890.01305963.495910.000011、建立截距维的随机效应模型,并进行Hausman检验,确定是选择随机效应亦或是固定效应模型,零假设:随机效应模型成立。截面维随机效应模型的设置
截面维随机效应模型的估计结果D即endentVariable:LNY?Method:PooledEGLS(Cross-sectionrandomeffects)Date:05/24/07Time:20:56Sample:19862005Includedobservations:20Cross-sectionsincluded:29Totalpool(balanced)observations:580SwamyandAroraestimatorofcomponentvariancesVariableCoefficientStd.Errort-StatisticProb.c-1.2662660.199089c-1.2662660.199089-6.360300LNK?0.7567330.01631446.38637LNDH?0.2780840.02008213.84711LNXH?0.4885100.0988494.942000LNNE1?-0.1295320.067090-1.930722LNCE1?0.3901600.0711465.483910RandomEffects(Cross)BEIJING-C-0.243423TIAN』N“C-0.042283HEBEI-C-0.043812SHANXI_D-C-0.113288NEIMENG-C-0.073589截面维随机效应模型的Hausman检验菜单项的选择0.00000.00000.00000.00000.05400.0000J■Pool:FAZHANMOXIWorkfile:SHSH02::yongxufazhanmoxi]Piew!IProcIObjectIPrintINameFreezeEstimateDefinePoolGenrSheet1CrossSectionIdentifiersRepresentationsEstimationOutputactionrandomeffects)Residuals►匚oefCovarianceMatrix匚oefficientTests►n<:-AAO,|||Fixed/RandomEffectsTesting卜RedundantEixedEffects-LikelihoodRatioSpreadsheet(stackeddata)...CorrelatedRandomEffects-HausmanTest*ntStd.Errort-StatisticProb.DescriptiveStatistics..UnitRootTest...360.199089-6.3603000.0000CointegrationTest...330.01631446.386370.0000Label340.02008213.847110.0000截面维随机效应模型Hausman检验的结果:Hausman检验的零假设是应当选择随机效应模型,小概率事件发生拒绝零假设选择固定效应模型CorrelatedRandomEffects-HausmanTestPool:FAZHANMOXITestcross-sectionrandomeffectsTestSummaryChi-Sq.StatisticChi-Sq.d.f.Prob.Cross-sectionrandom53.39400450.0000Cross-sectionrandomeffectstestcomparisons:VariableFixedRandomVar(Diff.)Prob.LNK?0.6907670.7567330.0001360.0000LNDH?0.1038980.2780840.0010820.0000LNXH?1.3497620.4885100.0219310.0000LNNE1?-0.165217-0.1295320.0007840.2025LNCE1?0.3528760.3901600.0017980.379212、13在时间维重复10、和11、的工作,确定数据适合采用何种模14、建立截面变截距模型,分析没有观察的截面单元因素的影响截面变截距模型的设置
截面变截距模型的估计结果DependentVariable:LNY?Method:PooledLeastSquaresDate:05/24/07Time:21:05Sample:19862005Includedobservations:20Cross-sectionsincluded:29Totalpool(balanced)observations:580VariableCoefficientStd.Errort-StatisticProb.C-0.7852040.267649-2.9337080.0035LNK?0.6907670.02006434.427310.0000LNDH?0.1038980.0385402.6958280.0072LNXH?1.3497620.1780527.5807240.0000LNNE1?-0.1652170.072697-2.2726610.0234LNCE1?0.3528760.0828214.2606880.0000FixedEffects(Cross)BEIJING-C-0.614424TIANJIN-C-0.436907HEBEI-C0.113717SHANXI_D-C-0.207641NEIMENG-C-0.209332LIAONING-C0.09565515、建立时期变截距模型,分析没有观察的时期因素的影响时期变截距模型的设置
时期变截距模型的估计结果D即endentVariable:LNY?Method:PooledLeastSquaresDate:05/24/07Time:21:08Sample:19862005Includedobservations:20Cross-sectionsincluded:29Totalpool(balanced)observations:580VariableCoefficientStd.Errort-StatisticProb.C-0.6582070.117502-5.6016470.0000LNK?0.7467130.01892639.453540.0000LNDH?0.3210070.01529420.989580.0000LNXH?0.2479490.0528904.6879810.0000LNNE1?0.0872650.0856731.0185830.3088LNCE1?-0.4359990.080745-5.3997150.0000FixedEffects(Period)1986-C-0.1907931987-C-0.1966561988-C-0.1490011989-C-0.1469821990-C-0.1120041991-C-0.10882016、在整个估计、检验构成中养成使用冻结和命名保存的习惯,以便撰写报告时调用。
T^ble:UNTITLEDWoricfile:SHSH02::Y(mgjciifazhanm・・・甲iewPrci匚|objazt|Print|Nmme|Edit+/-CellFmtGrid+/-TitleCcimments+/-|ABCDE11D即endentVariable:LNY?▲I2Method:PooledLeastSquaresI3Date:05/24/07Time:21:08I4Sample:19862005I5Includedobservations:20I6Cross-sectionsincluded:29ITotalpool(balanced)observations:580十VariableCoefficientStd.Errort-StatisticProb.111C-0.6582070.117502-5.6016470.0000I12LNK?0.7467130.01892639.453540.0000I13LNDH?0.3210070.01529420.989580.0000I14LNXH?0.2479490.0528904.6879810.0000I15LNNE1?0.0872650.0856731.0185830.3088I16LNCE1?-0.4359990.080745-5.3997150.0000I17FixedEffects(Period)1817、工作中注意使用工作文件窗口顶部的显示过滤器,简化你的窗口,以免眼花缭乱。过虑前
□Workfile::SHSH02-(e:\newdata\sh...|S^|ViewProc|Object|PrintSaveDetails+/-1ShowFetchStoreDeleteGenr|SampleRange:19862005-20obsDisplayFilter:*Sample:19062005-20obsEcSIncelguizhouSInce1shanxi_d===dwg」nc:巳1SIncelhainan0Ince1shanxi_x===dwg」nclhSIncelhebei0Incelsichuan=■==dwg」nkSIncelhenan0Inceltianjin===dwgjnlSIncelhljiang0Incelxinjiang=■==dwg」门门已1SIncelhubei0Incelyunnan===dwgjny0Incelhunan0Incelzhejiang=■==dwg_lny_02SInceljiangsuSInce2anhui回fazhanmoxiSInceljiangxi0Ince2beijingE]groupdSInceljilin0Ince2fujian0IncelanhuiSIncelliaoning0Ince2gansu0Incelbeijing
温馨提示
- 1. 本站所有资源如无特殊说明,都需要本地电脑安装OFFICE2007和PDF阅读器。图纸软件为CAD,CAXA,PROE,UG,SolidWorks等.压缩文件请下载最新的WinRAR软件解压。
- 2. 本站的文档不包含任何第三方提供的附件图纸等,如果需要附件,请联系上传者。文件的所有权益归上传用户所有。
- 3. 本站RAR压缩包中若带图纸,网页内容里面会有图纸预览,若没有图纸预览就没有图纸。
- 4. 未经权益所有人同意不得将文件中的内容挪作商业或盈利用途。
- 5. 人人文库网仅提供信息存储空间,仅对用户上传内容的表现方式做保护处理,对用户上传分享的文档内容本身不做任何修改或编辑,并不能对任何下载内容负责。
- 6. 下载文件中如有侵权或不适当内容,请与我们联系,我们立即纠正。
- 7. 本站不保证下载资源的准确性、安全性和完整性, 同时也不承担用户因使用这些下载资源对自己和他人造成任何形式的伤害或损失。
最新文档
- 收入售后回购租赁合同范例
- 2025借款质押用担保合同
- 太原市活塞接垃圾合同范例
- 2025计算机系统日常维护合同
- 2025什么是集体合同
- 公正赠与合同范例
- 活动板供货合同范例
- 公司提供劳务合同范例
- 正规家庭养殖合同范例
- 完整版100以内加减法混合运算4000道85
- 聘请专家的协议书(2篇)
- 2024年国家危险化学品生产单位安全管理人员考试题库(含答案)
- 《新的实验》教学课件1
- 《4.3用一元一次方程解决问题》教学设计
- 收二手贵重物品协议书范文
- 人教版七年级生物上册第二单元第一章第二节种子植物课件
- 大学生心理健康教育(中南大学版)学习通超星期末考试答案章节答案2024年
- 塔吊试题(有答案)201506
- 2024年重庆市中考数学真题卷(A)及答案解析
- 医用氧气安全培训课件
- 苏科版生物八年级下册 8.24.2 传染病的预防 -病毒 教案
评论
0/150
提交评论