我国国内生产总值的实证分析Word格式.docx

1、、X6。设定模型为：GDP=+U经查资料得国内生产总值样本观测数据（单位/亿元）：年份GDP进出口额财政支出职工工资总额税收收入上期GDP储蓄余额199018667.85560.13083.592951.12821.8616992.31210.2199121781.57225.83386.623323.92990.171610199226923.59119.63742.23939.23296.912312.3199335333.9112714642.34916.24255.33095.2199448197.920381.95792.626656.45126.884680.1199560793.

2、723499.96823.7281006038.045884.1199671176.624133.87937.5590806909.827647.619977897326967.29233.569405.38234.0410053.1199884402.326849.710798.189296.59262.811615.9199989677.129896.213187.679875.510682.5814666.7200099214.639273.215886.510656.212581.5118190.72001109655.242183.618902.5811830.915301.3822

3、327.6200120332.751378.222053.1513161.117636.4528121.72003135822.870483.524649.9514743.520017.31351192004159878.395539.128486.8916900.224165.6841416.52005184937.4116921.833930.2819789.928778.5448787.52006216314.4140971.540422.7323265.934804.3558575.92007265810.3166740.249781.352824445621.9767599.7200

4、8314045.4179921.562592.66337145422.37978585.22009340506.9150648.176299.9340288.16 59521.59100541.3 数据来自中国统计年鉴 二、模型的参数估计对设定模型用OLS法进行参数估计,用Eviews5对上表数据回归得：Dependent Variable: GDPMethod: Least SquaresDate: 06/29/11 Time: 20:09Sample: 1990 2009 Included observations: 20VariableCoefficientStd. Errort-Sta

5、tisticProb.X10.4646870.04152711.189910.0000X21.0994050.5206052.1117810.0546X31.8544330.6837492.7121550.0178X40.0980130.0829981.1809150.2588X50.7590800.06756111.23539X6-1.2842790.378693-3.3913490.0048C-2350.2981721.927-1.3649230.1954R-squared0.999706Mean dependent var124122.3Adjusted R-squared0.99957

6、1S.D. dependent var95623.17S.E. of regression1981.296Akaike info criterion18.29011Sum squared resid51031963Schwarz criterion18.63861Log likelihood-175.9011F-statistic7373.983Durbin-Watson stat1.313821Prob（F-statistic）0.000000回归结果如下：GDP=-2350.298+-1.364926 11.18993 2.111785 2.712161 1.18091 11.23540

7、-3.391354 =0.999706 =0.999571 = 7374.005 D.W.=1313820F=7374.005 （6，13）=2.92（显著性水平=0.05）表明模型从整体上看国内生产总值和解释变量间线形关系显著。三、检验及修正1 经济意义检验从上述回归结果可知：的系数为负值，说明国民生产总值随居民储蓄余额的增加而减少，这从理论上说不符合我国的实际情况；其他因素系数均为正，均不和经济原理相悖，具有经济意义：各系数表示国内生产总值对该因素的弹性大小。2统计意义检验从回归结果可以看出，模型的拟和优度非常好（=0.999706）， F统计量的值在给定显著性水平=0.05的情况下也较显

8、著。因为= 7374.00（6，13），表明模型的线性关系在95%的置信水平下显著成立.。但是X2、X4的t统计值均不显著。3.计量经济学检验（1）多重共线性检验 相关系数检验：用Eviews5求得解释变量的相关系数矩阵：1.0000000.9691790.9917940.9958250.7904600.9968650.9910170.9489190.9510890.7525850.9500810.9608840.9951810.8007630.9934930.9960780.8011940.9960410.9911650.8021560.8300140.991482 由此可知：解释变量、之间

9、存在高度正相关，模型存在严重多重共线性。下面对模型进行修正。模型修正：用逐步回归法修正模型由相关系数矩阵知解释变量X5和GDP相关性最强，故首先选取X5 做为基本变量和GDP建立一元回归模型： Y=1206.208+1.138675 （0.418440） （53.45104） 2 =0.9937 F=2857.014 D.W.=1.117717依次引入X3 、X6变量回归：引入X3 ：19 1990 2009-1393.5373037.490-0.4587790.65223.4106601.8228111.8710990.07860.7201990.2245413.2074240.00520.

10、9948080.9941987283.97720.762229.02E+0820.91158-204.62221628.7421.268140 引入X3 ，拟合优度得到提高，参数符号合理且参数统计量显著，故采纳该变量。 引入：252751.9581322.7232.0805240.05392.2067810.7579712.9114320.01020.6344520.0924466.8629150.3547030.0384029.2364730.9991800.9990262983.74519.016601.42E+0819.21575-186.16606499.4881.354897，拟合优

11、度再次提高，参数符号合理且参数统计量显著，故采纳该变量。 引入36-207.38322300.651-0.0901410.92942.9347960.8670593.3847710.00410.6701370.0916737.3101070.3578850.0369069.697292-0.5111510.331441-1.5422080.14390.9992920.9991042862.96918.969421.23E+0819.21836-184.69425295.1611.523732，拟合优度虽然得到了提高，但是参数符号为负值，表示GDP随财政支出增加而减少，和实际情况相悖，故将该变量

12、剔除。剔除，引入 21:052678.0091221.1702.1929850.04452.2767800.7003623.2508610.00540.6483440.0856057.5736290.3506080.0354999.876493-0.1330840.068361-1.9467830.07050.9993450.9991712753.33318.891331.14E+0819.14026-183.91335725.5631.606945引入，拟合优度再次提高，但是参数符号为负值表明我国GDP随税收收入增加而减少，和实际情况相悖，所以将之剔除。22Std.Error0.4085420.03081113.259652.8052140.5666054.9509120.00020.7345550.07122210.31356-0.6075290.152807-3.9757870.0012-2698.4361669.743-1.6160790.12690.9996010.9994942150.29518.39692