1、计量经济学实验报告实验目的：掌握自相关问题的检验以及相关的 Eviews 的操作方法。实验内容：消费总量的多少主要有 GDP 决定。为了考察 GDP 对消费总额的影响，可使用如下模型：Y = ；其中，X 表示i10iGDP，Y 表示消费总量。下表列出了中国 1990-2000 的 GDP 的 X 与消费总额 Y 的统计数据。年份 GDP（X ） 消费总额（Y） 年份 GDP（X ） 消费总额（Y）1990 18319.5 11365.2 1998 79003.3 46405.91991 21280.4 13145.9 1999 82673.2 49722.81992 25863.7 15952
2、.1 2000 89112.5 54617.21993 34500.7 20182.1 2001 98592.9 58927.41994 46690.7 26796 2002 107897.6 62798.51995 58510.5 33635 2003 121730.3 67493.51996 68330.4 40003.9 2004 142394.2 75439.71997 74894.2 43579.4一、估计回归方程OLS 法的估计结果如下：Y=2329.401+0.546950X（1.954322） （36.71110）R =0.990446， =0.989711，SE=2091.4
3、75，D.W.=0.478071。2R2二、进行序列相关性检验（1）图示检验法（2）回归检验法一阶回归检验二阶回归检验=1.144406e 0.343796e +te1-t 2-tt3）拉格朗日乘数（LM）检验法Breusch-Godfrey Serial Correlation LM Test:F-statistic 29.41781 Probability 0.000038Obs*R-squared 12.63731 Probability 0.001802Test Equation:Dependent Variable: RESIDMethod: Least SquaresDate: 1
4、2/17/12 Time: 21:51Variable Coefficient Std. Error t-Statistic Prob. C 37.31393 644.3315 0.057911 0.9549X -0.002008 0.009377 -0.214144 0.8344RESID(-1) 1.744086 0.234326 7.442998 0.0000RESID(-2) -1.088243 0.315853 -3.445408 0.0055R-squared 0.842487 Mean dependent var 4.37E-12Adjusted R-squared 0.7995
5、29 S.D. dependent var 2015.396S.E. of regression 902.3726 Akaike info criterion 16.67111Sum squared resid 8957040. Schwarz criterion 16.85992Log likelihood -121.0333 F-statistic 19.61188Durbin-Watson stat 2.360720 Prob(F-statistic) 0.000101C=37.31393 x=-0.002008 RESID(-1)=1.744086 RESID(-2)= -1.0882
6、43三、序列相关的补救Dependent Variable: DYMethod: Least SquaresDate: 12/17/12 Time: 22:07Sample(adjusted): 1991 2004Included observations: 14 after adjusting endpointsVariable Coefficient Std. Error t-Statistic Prob. C 2369.885 789.9844 2.999914 0.0111DX 0.465880 0.029328 15.88520 0.0000R-squared 0.954604 Me
7、an dependent var 13875.68Adjusted R-squared 0.950821 S.D. dependent var 5320.847S.E. of regression 1179.971 Akaike info criterion 17.11593Sum squared resid 16707973 Schwarz criterion 17.20722Log likelihood -117.8115 F-statistic 252.3397Durbin-Watson stat 0.521473 Prob(F-statistic) 0.000000（2）科克伦-奥科特
8、法估计模型Dependent Variable: YMethod: Least SquaresDate: 12/17/12 Time: 22:09Sample(adjusted): 1991 2004Included observations: 14 after adjusting endpointsConvergence achieved after 16 iterationsVariable Coefficient Std. Error t-Statistic Prob. C 55169.41 54542.80 1.011488 0.3335X 0.345292 0.057754 5.97
9、8675 0.0001AR(1) 0.961253 0.042004 22.88491 0.0000R-squared 0.998047 Mean dependent var 43478.53Adjusted R-squared 0.997691 S.D. dependent var 19591.16S.E. of regression 941.3171 Akaike info criterion 16.71985Sum squared resid 9746856. Schwarz criterion 16.85679Log likelihood -114.0389 F-statistic 2810.040Durbin-Watson stat 0.941831 Prob(F-statistic) 0.000000Inverted AR Roots .96
