下载文档原格式
第二章之迟辟智美创作（1）①对浙江省预算收入与全省生产总值的模型，用Eviews分析结果如下：Dependent Variable: YMethod: Least SquaresDate: 12/03/14 Time: 17:00Sample (adjusted): 1 33Included observations: 33 after adjustmentsVariable Coefficient Std. Error t-Statistic Prob.XCR-squared Mean dependent varAdjusted R-squared S.D. dependent varS.E. of regression Akaike info criterionSum squared resid Schwarz criterionLog likelihood Hannan-Quinn criter.F-statistic Durbin-Watson statProb(F-statistic)③关于浙江省财政预算收入与全省生产总值的模型，检验模型的显著性：1）可决系数为0.983702，说明所建模型整体上对样本数据拟合较好.2）对回归系数的t检验：t（β2）=43.25639>t0.025(31)=2.0395，对斜率系数的显著性检验标明，全省生产总值对财政预算总收入有显著影响.④用规范形式写出检验结果如下：(0.004072) (39.08196)t= (43.25639) （-3.948274）R2=0.983702 F=1871.115 n=33⑤经济意义是：全省生产总值每增加1亿元，财政预算总收入增加0.176124亿元.（2）当x=32000时，①进行点预测，由上可知Y=0.176124X—154.3063，代入可得：②进行区间预测：先由Eviews分析：由上表可知，当Xf=32000时，将相关数据代入计算获得：5481.6617—2.0395x175.2325x√1/33+1852223.473/675977068. 2≤即Yf的置信区间为（5481.6617—64.9649,5481.6617+64.9649）(3) 对浙江省预算收入对数与全省生产总值对数的模型，由Eviews分析结果如下：Dependent Variable: LNYMethod: Least SquaresDate: 12/03/14 Time: 18:00Sample (adjusted): 1 33Included observations: 33 after adjustmentsVariable Coefficient Std. Error t-Statistic Prob.LNXCR-squared Mean dependent varAdjusted R-squared S.D. dependent varS.E. of regression Akaike info criterionSum squared resid Schwarz criterionLog likelihood Hannan-Quinn criter.F-statistic Durbin-Watson statProb(F-statistic)③关于浙江省财政预算收入与全省生产总值的模型，检验其显著性：1）可决系数为0.963442，说明所建模型整体上对样本数据拟合较好.2）对回归系数的t检验：t（β2）=28.58268>t0.025(31)=2.0395，对斜率系数的显著性检验标明，全省生产总值对财政预算总收入有显著影响.④经济意义：全省生产总值每增长1%，财政预算总收入增长0.980275%（1）对建筑面积与建造单元本钱模型，用Eviews分析结果如下：Dependent Variable: YMethod: Least SquaresDate: 12/01/14 Time: 12:40Sample: 1 12Included observations: 12Variable Coefficient Std. Error t-Statistic Prob.XCR-squared Mean dependent varAdjusted R-squared S.D. dependent varS.E. of regression Akaike info criterionSum squared resid Schwarz criterionLog likelihood Hannan-Quinn criter.F-statistic Durbin-Watson statProb(F-statistic)由上可得：建筑面积与建造本钱的回归方程为：（2）经济意义：建筑面积每增加1万平方米，建筑单元本钱每平方米减少64.18400元.（3）②再进行区间估计：用Eviews分析：由上表可知，当Xf=4.5时，将相关数据代入计算获得：1556.647—2.228x31.73600x√1/12+43.5357/0.95387843≤即Yf的置信区间为（1556.647—478.1231, 1556.647+478.1231）第三章１）对出口货物总额计量经济模型，用Eviews分析结果如下：：Dependent Variable: YMethod: Least SquaresDate: 12/01/14 Time: 20:25Sample: 1994 2011Included observations: 18Variable Coefficient Std. Error t-Statistic Prob.X2X3CR-squared Mean dependent varAdjusted R-squared S.D. dependent varS.E. of regression Akaike info criterionSum squared resid8007316. Schwarz criterionLog likelihood Hannan-Quinn criter.F-statistic Durbin-Watson statProb(F-statistic)①由上可知，模型为：②对模型进行检验：1）可决系数是0.985838，修正的可决系数为0.983950，说明模型对样本拟合较好2）F检验，F=522.0976>F（2,15）=4.77，回归方程显著3）t检验，t统计量分别为X2的系数对应t值为10.58454，年夜于t（15）=2.131，系数是显著的，X3的系数对应t值为1.928512，小于t（15）=2.131，说明此系数是不显著的.（2）对对数模型，用Eviews分析结果如下：Dependent Variable: LNYMethod: Least SquaresDate: 12/01/14 Time: 20:25Sample: 1994 2011Included observations: 18Variable Coefficient Std. Error t-Statistic Prob.LNX2LNX3CR-squared Mean dependent varAdjusted R-squared S.D. dependent varS.E. of regression Akaike info criterionSum squared resid Schwarz criterionLog likelihood Hannan-Quinn criter.F-statistic Durbin-Watson statProb(F-statistic)①由上可知，模型为：LNY=-20.52048+1.564221 LNX2+1.760695 LNX3②对模型进行检验：1）可决系数是0.986295，修正的可决系数为0.984467，说明模型对样本拟合较好.2）F检验，F=539.7364> F（2,15）=4.77，回归方程显著.3）t检验，t统计量分别为-3.777363，17.57789，2.581229，均年夜于t（15）=2.131，所以这些系数都是显著的.（3）①（1）式中的经济意义：工业增加1亿元，出口货物总额增加0.135474亿元，人民币汇率增加1，出口货物总额增加18.85348亿元.②（2）式中的经济意义：工业增加额每增加1%，出口货物总额增加1.564221%，人民币汇率每增加1%，出口货物总额增加1.760695%（1）对家庭书刊消费对家庭月平均收入和户主受教育年数计量模型，由Eviews分析结果如下：Dependent Variable: YMethod: Least SquaresDate: 12/01/14 Time: 20:30Sample: 1 18Included observations: 18Variable Coefficient Std. Error t-Statistic Prob.XTCR-squared Mean dependent varAdjusted R-squared S.D. dependent varS.E. of regression Akaike info criterionSum squared resid Schwarz criterionLog likelihood Hannan-Quinn criter.F-statistic Durbin-Watson statProb(F-statistic)②对模型进行检验：1）可决系数是0.951235，修正的可决系数为0.944732，说明模型对样本拟合较好.2）F检验，F=539.7364> F（2,15）=4.77，回归方程显著. 3）t检验，t统计量分别为2.944186，10.06702，均年夜于t （15）=2.131，所以这些系数都是显著的.③经济意义：家庭月平均收入增加1元，家庭书刊年消费支出增加0.086450元，户主受教育年数增加1年，家庭书刊年消费支出增加52.37031元.（2）用Eviews分析：①Dependent Variable: YMethod: Least SquaresDate: 12/01/14 Time: 22:30Sample: 1 18Included observations: 18Variable Coefficient Std. Error t-Statistic Prob.TCR-squared Mean dependent varAdjusted R-squared S.D. dependent varS.E. of regression Akaike info criterionSum squared resid Schwarz criterionLog likelihood Hannan-Quinn criter.F-statistic Durbin-Watson statProb(F-statistic)②Dependent Variable: XMethod: Least SquaresDate: 12/01/14 Time: 22:34Sample: 1 18Included observations: 18Variable Coefficient Std. Error t-Statistic Prob.TCR-squared Mean dependent varAdjusted R-squared S.D. dependent varS.E. of regression Akaike info criterionSum squared resid4290746. Schwarz criterionLog likelihood Hannan-Quinn criter.F-statistic Durbin-Watson statProb(F-statistic)以上分别是y与T，X与T的一元回归模型分别是：（3）对残差进行模型分析，用Eviews分析结果如下：Dependent Variable: E1Method: Least SquaresDate: 12/03/14 Time: 20:39Sample: 1 18Included observations: 18Variable Coefficient Std. Error t-Statistic Prob.E2CR-squared Mean dependent varAdjusted R-squared S.D. dependent varS.E. of regression Akaike info criterionSum squared resid Schwarz criterionLog likelihood Hannan-Quinn criter.F-statistic Durbin-Watson statProb(F-statistic)模型为：（3）由上可知，β2与α2的系数是一样的.回归系数与被解释变量的残差系数是一样的，它们的变动规律是一致的.第五章(1)由Eviews软件分析得：Dependent Variable: YMethod: Least SquaresDate: 12/10/14 Time: 16:00Sample: 1 31Included observations: 31Variable Coefficient Std. Error t-Statistic Prob.XCR-squared Mean dependent varAdjusted R-squared S.D. dependent varS.E. of regression Akaike info criterionSum squared resid12220196 Schwarz criterionLog likelihood Hannan-Quinn criter.F-statistic Durbin-Watson statProb(F-statistic)由上表可知，2007年我国农村居民家庭人均消费支出（x）对人均纯收入（y）的模型为：（2）①由图形法检验由上图可知，模型可能存在异方差.②Goldfeld-Quanadt检验1）界说区间为1-12时，由软件分析得：Dependent Variable: Y1Method: Least SquaresDate: 12/10/14 Time: 11:34Sample: 1 12Included observations: 12Variable Coefficient Std. Error t-Statistic Prob.X1CR-squared Mean dependent varAdjusted R-squared S.D. dependent varS.E. of regression Akaike info criterionSum squared resid1772245. Schwarz criterionLog likelihood Hannan-Quinn criter.F-statistic Durbin-Watson statProb(F-statistic)得∑e1i2=1772245.2）界说区间为20-31时，由软件分析得：Dependent Variable: Y1Method: Least SquaresDate: 12/10/14 Time: 16:36Sample: 20 31Included observations: 12Variable Coefficient Std. Error t-Statistic Prob.X1CR-squared Mean dependent varAdjusted R-squared S.D. dependent varS.E. of regression Akaike info criterionSum squared resid7909670. Schwarz criterionLog likelihood Hannan-Quinn criter.F-statistic Durbin-Watson statProb(F-statistic)得∑e2i2=7909670.3）根据Goldfeld-Quanadt检验，F统计量为：在α=0.05水平下，分子分母的自由度均为10，查分布表得临界值F0.05（10,10）=2.98，因为F=4.4631> F0.05（10,10）=2.98，所以拒绝原假设，此检验标明模型存在异方差.（3）1）采纳WLS法估计过程中，①用权数w1=1/X,建立回归得：Dependent Variable: YMethod: Least SquaresDate: 12/09/14 Time: 11:13Sample: 1 31Included observations: 31Weighting series: W1Variable Coefficient Std. Error t-Statistic Prob.XCWeighted StatisticsR-squared Mean dependent varAdjusted R-squared S.D. dependent varS.E. of regression Akaike info criterionSum squared resid8352726. Schwarz criterionLog likelihood Hannan-Quinn criter.F-statistic Durbin-Watson statProb(F-statistic)Unweighted StatisticsR-squared Mean dependent varAdjusted R-squared S.D. dependent varS.E. of regression Sum squared resid14484289 Durbin-Watson stat对此模型进行White检验得：Heteroskedasticity Test: WhiteF-statistic Prob. F(2,28)Obs*R-squared Prob. Chi-Square(2)Scaled explained SS Prob. Chi-Square(2)Test Equation:Dependent Variable: WGT_RESID^2Method: Least SquaresDate: 12/10/14 Time: 21:13Sample: 1 31Included observations: 31Collinear test regressors dropped from specificationVariable Coefficient Std. Error t-Statistic Prob.C1045682.WGT^21173622.X*WGT^2R-squared Mean dependent varAdjusted R-squared S.D. dependent varS.E. of regression Akaike info criterionSum squared resid 1.40E+13 Schwarz criterionLog likelihood Hannan-Quinn criter.F-statistic Durbin-Watson statProb(F-statistic)从上可知，nR2=0.649065，比力计算的统计量的临界值，因为nR2=0.649065<0.05（2）=5.9915，所以接受原假设，该模型消除异方差.估计结果为：t=（11.97157）（-0.972298）②用权数w2=1/x2,用回归分析得：Dependent Variable: YMethod: Least SquaresDate: 12/09/14 Time: 21:08Sample: 1 31Included observations: 31Weighting series: W2Variable Coefficient Std. Error t-Statistic Prob.XCWeighted StatisticsR-squared Mean dependent varAdjusted R-squared S.D. dependent varS.E. of regression Akaike info criterionSum squared resid6320554. Schwarz criterionLog likelihood Hannan-Quinn criter.F-statistic Durbin-Watson statProb(F-statistic)Unweighted StatisticsR-squared Mean dependent varAdjusted R-squared S.D. dependent varS.E. of regression Sum squared resid19268334Durbin-Watson stat对此模型进行White检验得：Heteroskedasticity Test: WhiteF-statistic Prob. F(3,27)Obs*R-squared Prob. Chi-Square(3)Scaled explained SS Prob. Chi-Square(3)Test Equation:Dependent Variable: WGT_RESID^2Method: Least SquaresDate: 12/10/14 Time: 21:29Sample: 1 31Included observations: 31Variable Coefficient Std. Error t-Statistic Prob.CWGT^22240181.X^2*WGT^2X*WGT^2R-squared Mean dependent varAdjusted R-squared S.D. dependent varS.E. of regression Akaike info criterionSum squared resid 5.10E+12 Schwarz criterionLog likelihood Hannan-Quinn criter.F-statistic Durbin-Watson statProb(F-statistic)从上可知，nR2=0.999322，比力计算的统计量的临界值，因为nR2=0.999322<0.05（2）=5.9915，所以接受原假设，该模型消除异方差.估计结果为：t=（10.70922）（-1.841272）③用权数w3=1/sqr（x）,用回归分析得：Dependent Variable: YMethod: Least SquaresDate: 12/09/14 Time: 21:35Sample: 1 31Included observations: 31Weighting series: W3Variable Coefficient Std. Error t-Statistic Prob.XCWeighted StatisticsR-squared Mean dependent varAdjusted R-squared S.D. dependent varS.E. of regression Akaike info criterionSum squared resid9990985. Schwarz criterionLog likelihood Hannan-Quinn criter.F-statistic Durbin-Watson statProb(F-statistic)Unweighted StatisticsR-squared Mean dependent varAdjusted R-squared S.D. dependent varS.E. of regression Sum squared resid12717412 Durbin-Watson stat对此模型进行White检验得：Heteroskedasticity Test: WhiteF-statistic Prob. F(2,28)Obs*R-squared Prob. Chi-Square(2)Scaled explained SS Prob. Chi-Square(2)Test Equation:Dependent Variable: WGT_RESID^2Method: Least SquaresDate: 12/09/14 Time: 20:36Sample: 1 31Included observations: 31Collinear test regressors dropped from specificationVariable Coefficient Std. Error t-Statistic Prob.C1212308.2141958.WGT^21301839.X^2*WGT^2R-squared Mean dependent varAdjusted R-squared S.D. dependent varS.E. of regression Akaike info criterionSum squared resid 2.17E+13 Schwarz criterionLog likelihood Hannan-Quinn criter.F-statistic Durbin-Watson statProb(F-statistic)从上可知，nR2=0.911022，比力计算的统计量的临界值，因为nR2=0.911022<0.05（2）=5.9915，所以接受原假设，该模型消除异方差.估计结果为：t=（13.52507）（-0.151390）经过检验发现，用权数w1的效果最好，所以综上可知，即修改后的结果为：t=（11.97157）（-0.972298）第六章(1)建立居民收入-消费模型，用Eviews分析结果如下：Dependent Variable: YMethod: Least SquaresDate: 12/20/14 Time: 14:22Sample: 1 19Included observations: 19Variable Coefficient Std. Error t-Statistic Prob.XCR-squared Mean dependent varAdjusted R-squared S.D. dependent varS.E. of regression Akaike info criterionSum squared resid Schwarz criterionLog likelihood Hannan-Quinn criter.F-statistic Durbin-Watson statProb(F-statistic)所得模型为：Se=(0.012877)(12.39919)t=(53.62068)(6.446390)（2）1）检验模型中存在的问题①做出残差图如下：残差的变动有系统模式，连续为正和连续为负，标明残差项存在一阶自相关.②该回归方程可决系数较高，回归系数均显著.对样本量为19，一个解释变量的模型，5%的显著水平，查DW统计表可知，dL=1.180，dU=1.401，模型中DW=0.574663,<dL,显然模型中有自相关.③对模型进行BG检验，用Eviews分析结果如下：Breusch-Godfrey Serial Correlation LM Test:F-statistic Prob. F(2,15)Obs*R-squared Prob. Chi-Square(2)Test Equation:Dependent Variable: RESIDMethod: Least SquaresDate: 12/20/14 Time: 15:03Sample: 1 19Included observations: 19Presample missing value lagged residuals set to zero.Variable Coefficient Std. Error t-Statistic Prob.XCRESID(-1)RESID(-2)R-squared Mean dependent varAdjusted R-squared S.D. dependent varS.E. of regression Akaike info criterionSum squared resid Schwarz criterionLog likelihood Hannan-Quinn criter.F-statistic Durbin-Watson statProb(F-statistic)如上表显示，LM=TR2=7.425088，其p值为0.0244，标明存在自相关.2）对模型进行处置：①采用广义差分法a)为估计自相关系数ρ.对et进行滞后一期的自回归，用EViews分析结果如下：Dependent Variable: EMethod: Least SquaresDate: 12/20/14 Time: 15:04Sample (adjusted): 2 19Included observations: 18 after adjustmentsVariable Coefficient Std. Error t-Statistic Prob.E(-1)R-squared Mean dependent varAdjusted R-squared S.D. dependent varS.E. of regression Akaike info criterionSum squared resid Schwarz criterionLog likelihood Hannan-Quinn criter.Durbin-Watson statb)对原模型进行广义差分回归，用Eviews进行分析所得结果如下：Dependent Variable: Y-0.657352*Y(-1)Method: Least SquaresDate: 12/20/14 Time: 15:04Sample (adjusted): 2 19Included observations: 18 after adjustmentsVariable Coefficient Std. Error t-Statistic Prob.CX-0.657352*X(-1)R-squared Mean dependent varAdjusted R-squared S.D. dependent varS.E. of regression Akaike info criterionSum squared resid Schwarz criterionLog likelihood Hannan-Quinn criter.F-statistic Durbin-Watson statProb(F-statistic)由上图可知回归方程为：Yt*=35.97761+0.668695Xt*Se=(8.103546)(0.020642)t=(4.439737)(32.39512)由于使用了广义差分数据，样本容量减少了1个，为18个.查5%显著水平的DW统计表可知，dL=1.158,dU=1.391模型中DW=1,830746，du<DW<4- dU，说明在5%的显著水平下广义差分模型中已无自相关.可决系数R2，t，F统计量也均到达理想水平.由此最终的消费模型为：Yt=104.9987+0.668695Xt②用科克伦-奥克特迭代法，用EVIews分析结果如下：Dependent Variable: YMethod: Least SquaresDate: 12/20/14 Time: 15:15Sample (adjusted): 2 19Included observations: 18 after adjustmentsConvergence achieved after 5 iterationsVariable Coefficient Std. Error t-Statistic Prob.CXAR(1)R-squared Mean dependent varAdjusted R-squared S.D. dependent varS.E. of regression Akaike info criterionSum squared resid Schwarz criterionLog likelihood Hannan-Quinn criter.F-statistic Durbin-Watson statProb(F-statistic)Inverted AR Roots .63所得方程为：（3）经济意义：人均实际收入每增加1元，平均说来人均时间消费支出将增加0.669262元.（1）针对对数模型，用Eviews分析结果如下：Dependent Variable: LNYMethod: Least SquaresDate: 12/27/14 Time: 16:13Sample: 1980 2000Included observations: 21Variable Coefficient Std. Error t-Statistic Prob.LNXCR-squared Mean dependent varAdjusted R-squared S.D. dependent varS.E. of regression Akaike info criterionSum squared resid Schwarz criterionLog likelihood Hannan-Quinn criter.F-statistic Durbin-Watson statProb(F-statistic)所得模型为：se=(0.038897) (0.241025)t=(24.45123) (9.007529)2）检验模型的自相关性该回归方程可决系数较高，回归系数均显著.对样本量为21，一个解释变量的模型，5%的显著水平，查DW统计表可知，dL=1.221，dU=1.420，模型中DW=1.159788<dL,显然模型中有自相关.(2)用广义差分法处置模型：1）为估计自相关系数ρ.对et进行滞后一期的自回归，用EViews分析结果如下：Dependent Variable: EMethod: Least SquaresDate: 12/27/14 Time: 16:18Sample (adjusted): 1982 2000Included observations: 19 after adjustmentsVariable Coefficient Std. Error t-Statistic Prob.E(-1)R-squared Mean dependent varAdjusted R-squared S.D. dependent varS.E. of regression Akaike info criterionSum squared resid2848090. Schwarz criterionLog likelihood Hannan-Quinn criter.Durbin-Watson stat2）对原模型进行广义差分回归，用Eviews进行分析所得结果如下：Dependent Variable: Y+0.012872*Y(-1)Method: Least SquaresDate: 12/27/14 Time: 21:06Sample (adjusted): 1981 2000Included observations: 20 after adjustmentsVariable Coefficient Std. Error t-Statistic Prob.CX+0.012872*X(-1)R-squared Mean dependent varAdjusted R-squared S.D. dependent varS.E. of regression Akaike info criterionSum squared resid2882022. Schwarz criterionLog likelihood Hannan-Quinn criter.F-statistic Durbin-Watson statProb(F-statistic)由上图可知回归方程为：Yt*=-104.9645+6.653757Xt*Se=(197.7928)( 0.304157)t=(-0.530679)( 21.87605)由于使用了广义差分数据，样本容量减少了1个，为20个.查5%显著水平的DW统计表可知，dL=1.201,dU=1.411模型中DW=1.8222596，du<DW<4- dU，说明在5%的显著水平下广义差分模型中已无自相关.可决系数R2，t，F统计量也均到达理想水平.由此最终的模型为：（3）对此模型，用Eviews分析结果如下：Dependent Variable: LNY1Method: Least SquaresDate: 12/27/14 Time: 22:16Sample (adjusted): 1981 2000Included observations: 20 after adjustmentsVariable Coefficient Std. Error t-Statistic Prob.LNX1CR-squared Mean dependent varAdjusted R-squared S.D. dependent varS.E. of regression Akaike info criterionSum squared resid Schwarz criterionLog likelihood Hannan-Quinn criter.F-statistic Durbin-Watson statProb(F-statistic)由题目可知，此模型样本容量为20，查5%显著水平的DW 统计表可知，dL=1.201,dU=1.411模型中DW=1.590363，du<DW<4- dU，说明在5%的显著水平此模型中无自相关.可决系数R2，t，F统计量也均到达理想水平。
