计量经济学-eviews实验报告

计量经济学作业院系：商学院国贸三班教室：高辉姓名：吴谧学号：2007080103221INDEX问题…………………………………………………………………………………2模型设定……………………………………………………………………………3检验异方差…………………………………………………………………………4图形检验………………………………………………………………………4Glejser检验……………………………………………………………………5White检验……………………………………………………………………6调整异方差…………………………………………………………………………62习题5.8表5.13给出的是1998年我国重要制造业销售收入与销售利润的数据表5.13我国重要制造工业1998年销售利润与销售收入情况行业名称销售利润销售收汝行业名称销售利润销售收入食品加工业187.253180.44医药制造业238.711264.1食品制造业111.421119.88化学纤维制品81.57779.46饮料制造业205.421489.89橡胶制品业77.84692.08烟草加工业183.871328.59塑料制品业144.341345纺织业316.793862.9非金属矿制品339.262866.14服装制品业157.71779.1黑色金属冶炼367.473868.28皮革羽绒制品81.731081.77有色金属冶炼144.291535.16木材加工业35.67443.74金属制品业201.421948.12家具制造业31.06226.78普通机械制造354.692351.68造纸及纸品业134.41124.94专用设备制造238.161714.73印刷业90.12499.83交通运输设备511.944011.53文教体育用品54.4504.44电子机械制造409.833286.15石油加工业194.452363.8电子通讯设备508.154499.19化学原料纸品502.614195.22仪器仪表设备72.46663.68试完成以下问题：1）求销售利润与销售收入的样本回归函数，并对模型进行经济意义检验和统计检验；2）分别用图形法、Glejser方法、White方法检验模型是否存在异方差；3）如果模型存在异方差，选用适当的方法对异方差性进行修正。31）假定销售利润与销售收入之间满足线性约束，则理论模型设定为Yi=β1+β2XI+ui其中，Yi表示销售利润，表示销售收入。DependentVariable:YMethod:LeastSquaresDate:12/26/09Time:14:45Sample:128Includedobservations:28VariableCoefficientStd.Errort-StatisticProb.C12.0356419.517790.6166500.5428X0.1043930.00844112.366700.0000R-squared0.854696Meandependentvar213.4650AdjustedR-squared0.849107S.D.dependentvar146.4895S.E.ofregression56.90368Akaikeinfocriterion10.98935Sumsquaredresid84188.74Schwarzcriterion11.08450Loglikelihood-151.8508Hannan-Quinncriter.11.01844F-statistic152.9353Durbin-Watsonstat1.212795Prob(F-statistic)0.000000图1估计结果为Yˆi=12.03564+0.104393Xi（0.61665）（12.3667）R2=0.8547，F=152.94括号内为t统计量值。a)经济意义检验：所估计得参数βˆ1=0.104393，说明销售收入（X）没相差1亿元，可导致销售利润（Y）相差0.104393亿元。随着销售收入的增加，销售利润的平均水平是不断提高的，符合经济意义。b)拟合优度的度量：由此估计参数课件，该模型R2=0.8547可绝系数很高，说明所建模型整体上对样本数据拟合较好，即解释变量“销售收入（X）”对被解释变量“销售利润（Y）”的绝大部分作出解释。c)对于回归系数的t检验：在给定显著性水平α=0.05,在t分布表中查处自由度为n-2=26的临界值t0.025（26）=2.056，由于t（βˆ0）=0.616650t0.025（26）=2.056，对c的系数不显著影响：由于t（βˆ1）=12.3667t0.025（26）=2.056，对X的系数t检验显著影响。这表明，销售收入（X）对销售利润（Y）有显著影响。42）检验异方差图形分析检验⑴观察销售利润（Y）与销售收入（X）的相关图(图1)：SCATXY010020030040050060001,0002,0003,0004,0005,000XY图2从图中可以看出，随着销售收入的增加，销售利润的平均水平不断提高，但离散程度也逐步扩大。这说明变量之间可能存在递增的异方差性。⑵残差分析图3图3显示回归方程的残差分布有明显的扩大趋势，即表明存在异方差性。-200-150-100-50050100510152025RESID5Glejser检验⑴建立回归模型（结果同图1所示）。⑵生成新变量序列GENRE=ABS(RESID)⑶分别建立新残差序列（E）对各解释变量（X/X^2/X^(1/2)/X^(－1)/X^(－2)/X^(－1/2)）的回归模型：LSECX，回归结果如图4、5、6、7、8、9所示。DependentVariable:EMethod:LeastSquaresDate:12/26/09Time:17:29Sample:128Includedobservations:28VariableCoefficientStd.Errort-StatisticProb.C12.2380810.618521.1525230.2596X0.0152670.0045933.3242810.0026R-squared0.298262Meandependentvar41.69584AdjustedR-squared0.271272S.D.dependentvar36.26524S.E.ofregression30.95804Akaikeinfocriterion9.771892Sumsquaredresid24918.40Schwarzcriterion9.867049Loglikelihood-134.8065Hannan-Quinncriter.9.800982F-statistic11.05084Durbin-Watsonstat1.727724Prob(F-statistic)0.002643图4DependentVariable:EMethod:LeastSquaresDate:12/26/09Time:17:32Sample:128Includedobservations:28VariableCoefficientStd.Errort-StatisticProb.C27.057248.2323173.2867100.0029X^22.74E-061.02E-062.6900010.0123R-squared0.217718Meandependentvar41.69584AdjustedR-squared0.187630S.D.dependentvar36.26524S.E.ofregression32.68642Akaikeinfocriterion9.880546Sumsquaredresid27778.46Schwarzcriterion9.975703Loglikelihood-136.3276Hannan-Quinncriter.9.909636F-statistic7.236107Durbin-Watsonstat1.690452Prob(F-statistic)0.012315图56DependentVariable:EMethod:LeastSquaresDate:12/26/09Time:17:35Sample:128Includedobservations:28VariableCoefficientStd.Errort-StatisticProb.C-15.6781817.09598-0.9170680.3675X^(1/2)1.3861930.3891973.5616770.0014R-squared0.327914Meandependentvar41.69584AdjustedR-squared0.302065S.D.dependentvar36.26524S.E.ofregression30.29690Akaikeinfocriterion9.728717Sumsquaredresid23865.45Schwarzcriterion9.823874Loglikelihood-134.2020Hannan-Quinncriter.9.757807F-statistic12.68554Durbin-Watsonstat1.748719Prob(F-statistic)0.001450图6DependentVariable:EMethod:LeastSquaresDate:12/26/09Time:17:36Sample:128Includedobservations:28VariableCoefficientStd.Errort-StatisticProb.C59.388768.9663786.6234950.0000X^(-1)-19128.427040.292-2.7169920.0116R-squared0.221138Meandependentvar41.69584AdjustedR-squared0.191182S.D.dependentvar36.26524S.E.ofregression32.61490Akaikeinfocriterion9.876165Sumsquaredresid27657.02Schwarzcriterion9.971322Loglikelihood-136.2663Hannan-Quinncriter.9.905255F-statistic7.382044Durbin-Watsonstat1.846954Prob(F-statistic)0.011562图77DependentVariable:EMethod:LeastSquaresDate:12/26/09Time:17:37Sample:128Includedobservations:28VariableCoefficientStd.Errort-StatisticProb.C46.935017.1987506.5198830.0000X^(-2)-3230052.1792995.-1.8014840.0832R-squared0.110970Meandependentvar41.69584AdjustedR-squared0.076776S.D.dependentvar36.26524S.E.ofregression34.84529Akaikeinfocriterion10.00846Sumsquaredresid31569.05Schwarzcriterion10.10362Loglikelihood-138.1185Hannan-Quinncriter.10.03755F-statistic3.245344Durbin-Watsonstat1.768007Prob(F-statistic)0.083236图8DependentVariable:EMethod:LeastSquaresDate:12/26/09Tim