计量经济学-庞皓-第三版课后答案(共93页).docx

《计量经济学-庞皓-第三版课后答案(共93页).docx》由会员分享，可在线阅读，更多相关《计量经济学-庞皓-第三版课后答案(共93页).docx（93页珍藏版）》请在得力文库 - 分享文档赚钱的网站上搜索。

1、精选优质文档-倾情为你奉上 第二章 简单线性回归模型2.1（1） 首先分析人均寿命与人均GDP的数量关系，用Eviews分析：Dependent Variable: YMethod: Least SquaresDate: 12/27/14 Time: 21:00Sample: 1 22Included observations: 22VariableCoefficientStd. Errort-StatisticProb.C56.647941.28.889920.0000X10.0.4.0.0001R-squared0.Mean dependent var62.50000Adjusted R-

2、squared0.S.D. dependent var10.08889S.E. of regression7.Akaike info criterion6.Sum squared resid1013.000Schwarz criterion6.Log likelihood-73.34257Hannan-Quinn criter.6.F-statistic22.20138Durbin-Watson stat0.Prob(F-statistic)0.有上可知，关系式为y=56.64794+0.x1关于人均寿命与成人识字率的关系，用Eviews分析如下：Dependent Variable: YMe

3、thod: Least SquaresDate: 11/26/14 Time: 21:10Sample: 1 22Included observations: 22VariableCoefficientStd. Errort-StatisticProb.C38.794243.10.983400.0000X20.0.7.0.0000R-squared0.Mean dependent var62.50000Adjusted R-squared0.S.D. dependent var10.08889S.E. of regression5.Akaike info criterion6.Sum squa

4、red resid605.2873Schwarz criterion6.Log likelihood-67.67792Hannan-Quinn criter.6.F-statistic50.62761Durbin-Watson stat1.Prob(F-statistic)0.由上可知，关系式为y=38.79424+0.x2关于人均寿命与一岁儿童疫苗接种率的关系，用Eviews分析如下：Dependent Variable: YMethod: Least SquaresDate: 11/26/14 Time: 21:14Sample: 1 22Included observations: 22

5、VariableCoefficientStd. Errort-StatisticProb.C31.799566.4.0.0001X30.0.4.0.0001R-squared0.Mean dependent var62.50000Adjusted R-squared0.S.D. dependent var10.08889S.E. of regression7.Akaike info criterion6.Sum squared resid987.6770Schwarz criterion6.Log likelihood-73.06409Hannan-Quinn criter.6.F-stati

6、stic23.28338Durbin-Watson stat0.Prob(F-statistic)0.由上可知，关系式为y=31.79956+0.x3（2）关于人均寿命与人均GDP模型，由上可知，可决系数为0.，说明所建模型整体上对样本数据拟合较好。 对于回归系数的t检验：t（1）=4.t0.025(20)=2.086，对斜率系数的显著性检验表明，人均GDP对人均寿命有显著影响。关于人均寿命与成人识字率模型，由上可知，可决系数为0.，说明所建模型整体上对样本数据拟合较好。对于回归系数的t检验：t（2）=7.t0.025(20)=2.086，对斜率系数的显著性检验表明，成人识字率对人均寿命有显著

7、影响。关于人均寿命与一岁儿童疫苗的模型，由上可知，可决系数为0.，说明所建模型整体上对样本数据拟合较好。 对于回归系数的t检验：t（3）=4.t0.025(20)=2.086，对斜率系数的显著性检验表明，一岁儿童疫苗接种率对人均寿命有显著影响。2.2（1）对于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 adjustmentsVari

8、ableCoefficientStd. Errort-StatisticProb.X0.0.43.256390.0000C-154.306339.08196-3.0.0004R-squared0.Mean dependent var902.5148Adjusted R-squared0.S.D. dependent var1351.009S.E. of regression175.2325Akaike info criterion13.22880Sum squared resid.7Schwarz criterion13.31949Log likelihood-216.2751Hannan-Q

9、uinn criter.13.25931F-statistic1871.115Durbin-Watson stat0.Prob(F-statistic)0.由上可知，模型的参数：斜率系数0.，截距为154.3063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.，说明所建模型整体上对样本数据拟合较好。2）对于回归系数的t检验：t（2）=43.25639t0.025(31)=2.0395，对斜率系数的显著性检验表明，全省生产总值对财政预算总收入有显著影响。用规范形式写出检验结果如下：Y=0.X154.3063 (0.) (39.08196)t= (43.25639

10、) （-3.）R2=0. F=1871.115 n=33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0.亿元。（2）当x=32000时，进行点预测，由上可知Y=0.X154.3063，代入可得：Y= Y=0.*32000154.3063=5481.6617进行区间预测：先由Eviews分析：XYMean6000.441902.5148Median2689.280209.3900Maximum27722.314895.410Minimum123.720025.87000Std. Dev.7608.0211351.009Skewness1.1.Kurtosis4.4.Jarque-Be

11、ra12.6906818.69063Probability0.0.Sum.529782.99Sum Sq. Dev.1.85E+09Observations3333由上表可知，x2=（XiX）2=2x(n1)= 7608.0212 x (331)=.473(XfX)2=(320006000.441)2=.2当Xf=32000时，将相关数据代入计算得到：5481.66172.0395x175.2325x1/33+.473/.2Yf5481.6617+2.0395x175.2325x1/33+.473/.2即Yf的置信区间为（5481.661764.9649, 5481.6617+64.9649）

12、(3) 对于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 adjustmentsVariableCoefficientStd. Errort-StatisticProb.LNX0.0.28.582680.0000C-1.0.-7.0.0000R-squared0.Mean dependent var5.Adjusted R

13、-squared0.S.D. dependent var1.S.E. of regression0.Akaike info criterion0.Sum squared resid3.Schwarz criterion0.Log likelihood-8.Hannan-Quinn criter.0.F-statistic816.9699Durbin-Watson stat0.Prob(F-statistic)0.模型方程为：lnY=0.lnX-1.由上可知，模型的参数：斜率系数为0.，截距为-1.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.，说明所建模型整体上对

14、样本数据拟合较好。2）对于回归系数的t检验：t（2）=28.58268t0.025(31)=2.0395，对斜率系数的显著性检验表明，全省生产总值对财政预算总收入有显著影响。经济意义：全省生产总值每增长1%，财政预算总收入增长0.%2.4（1）对建筑面积与建造单位成本模型，用Eviews分析结果如下：Dependent Variable: YMethod: Least SquaresDate: 12/01/14 Time: 12:40Sample: 1 12Included observations: 12VariableCoefficientStd. Errort-StatisticProb

15、.X-64.184004.-13.344340.0000C1845.47519.2644695.796880.0000R-squared0.Mean dependent var1619.333Adjusted R-squared0.S.D. dependent var131.2252S.E. of regression31.73600Akaike info criterion9.Sum squared resid10071.74Schwarz criterion9.Log likelihood-57.42275Hannan-Quinn criter.9.F-statistic178.0715D

16、urbin-Watson stat1.Prob(F-statistic)0.由上可得：建筑面积与建造成本的回归方程为：Y=1845.475-64.18400X（2）经济意义：建筑面积每增加1万平方米，建筑单位成本每平方米减少64.18400元。（3）首先进行点预测，由Y=1845.475-64.18400X得，当x=4.5，y=1556.647再进行区间估计：用Eviews分析：YXMean1619.3333.Median1630.0003.Maximum1860.0006.Minimum1419.0000.Std. Dev.131.22521.Skewness0.-0.Kurtosis2.1

17、.Jarque-Bera0.0.Probability0.0.Sum19432.0042.28000Sum Sq. Dev.743.53567Observations1212由上表可知，x2=（XiX）2=2x(n1)= 1. x (121)=43.5357(XfX)2=(4.53.)2=0.当Xf=4.5时，将相关数据代入计算得到：1556.6472.228x31.73600x1/12+43.5357/0.Yf1556.647+2.228x31.73600x1/12+43.5357/0.即Yf的置信区间为（1556.647478.1231, 1556.647+478.1231）3.1（1）对

18、百户拥有家用汽车量计量经济模型，用Eviews分析结果如下：Dependent Variable: YMethod: Least SquaresDate: 11/25/14 Time: 12:38Sample: 1 31Included observations: 31VariableCoefficientStd. Errort-StatisticProb.X25.1.4.0.0002X3-0.0.-2.0.0069X4-2.0.-4.0.0002C246.854051.975004.0.0001R-squared0.Mean dependent var16.77355Adjusted R-s

19、quared0.S.D. dependent var8.S.E. of regression5.Akaike info criterion6.Sum squared resid682.2795Schwarz criterion6.Log likelihood-91.90460Hannan-Quinn criter.6.F-statistic17.95108Durbin-Watson stat1.Prob(F-statistic)0.得到模型得：Y=246.8540+5.X2-0. X3-2. X4对模型进行检验：1） 可决系数是0.，修正的可决系数为0.，说明模型对样本拟合较好2） F检验，F

20、=17.95108F（3,27）=3.65，回归方程显著。3）t检验，t统计量分别为4.，4.，-2.，-4.，均大于t（27）=2.0518，所以这些系数都是显著的。依据：1） 可决系数越大，说明拟合程度越好2） F的值与临界值比较，若大于临界值，则否定原假设，回归方程是显著的；若小于临界值，则接受原假设，回归方程不显著。3） t的值与临界值比较，若大于临界值，则否定原假设，系数都是显著的；若小于临界值，则接受原假设，系数不显著。（2）经济意义：人均增加万元，百户拥有家用汽车增加5.辆，城镇人口比重增加个百分点，百户拥有家用汽车减少0.辆，交通工具消费价格指数每上升，百户拥有家用汽车减少2.

21、辆。（3）用EViews分析得：Dependent Variable: YMethod: Least SquaresDate: 12/08/14 Time: 17:28Sample: 1 31Included observations: 31VariableCoefficientStd. Errort-StatisticProb.X25.1.5.0.0000LNX3-22.810056.-3.0.0023LNX4-230.848149.46791-4.0.0001C1148.758228.29175.0.0000R-squared0.Mean dependent var16.77355Adju

22、sted R-squared0.S.D. dependent var8.S.E. of regression4.Akaike info criterion6.Sum squared resid629.3818Schwarz criterion6.Log likelihood-90.65373Hannan-Quinn criter.6.F-statistic20.21624Durbin-Watson stat1.Prob(F-statistic)0.模型方程为：Y=5. X2-22.81005 LNX3-230.8481 LNX4+1148.758此分析得出的可决系数为0.0.，拟合程度得到了提

23、高，可这样改进。3.2（）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: 18VariableCoefficientStd. Errort-StatisticProb.X20.0.10.584540.0000X318.853489.1.0.0729C-18231.588638.216-2.0.0520R-squared0.Mean dependent var6619.191

24、Adjusted R-squared0.S.D. dependent var5767.152S.E. of regression730.6306Akaike info criterion16.17670Sum squared resid.Schwarz criterion16.32510Log likelihood-142.5903Hannan-Quinn criter.16.19717F-statistic522.0976Durbin-Watson stat1.Prob(F-statistic)0.由上可知，模型为：Y = 0.X2 + 18.85348X3 - 18231.58对模型进行检

25、验：1）可决系数是0.，修正的可决系数为0.，说明模型对样本拟合较好2）F检验，F=522.0976F（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，大于t（15）=2.131，系数是显著的，X3的系数对应t值为1.，小于t（15）=2.131，说明此系数是不显著的。 （2）对于对数模型，用Eviews分析结果如下：Dependent Variable: LNYMethod: Least SquaresDate: 12/01/14 Time: 20:25Sample: 1994 2011Included observations: 18Var

26、iableCoefficientStd. Errort-StatisticProb.LNX21.0.17.577890.0000LNX31.0.2.0.0209C-20.520485.-3.0.0018R-squared0.Mean dependent var8.Adjusted R-squared0.S.D. dependent var0.S.E. of regression0.Akaike info criterion-1.Sum squared resid0.Schwarz criterion-1.Log likelihood14.66782Hannan-Quinn criter.-1.

27、F-statistic539.7364Durbin-Watson stat0.Prob(F-statistic)0.由上可知，模型为：LNY=-20.52048+1. LNX2+1. LNX3对模型进行检验：1）可决系数是0.，修正的可决系数为0.，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.，17.57789，2.，均大于t（15）=2.131，所以这些系数都是显著的。（3）（1）式中的经济意义：工业增加1亿元，出口货物总额增加0.亿元，人民币汇率增加1，出口货物总额增加18.85348亿元。（2）式中的经

28、济意义：工业增加额每增加1%，出口货物总额增加1.%，人民币汇率每增加1%，出口货物总额增加1.%3.3（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: 18VariableCoefficientStd. Errort-StatisticProb.X0.0.2.0.0101T52.370315.10.067020.0000C-50.0163849.46

29、026-1.0.3279R-squared0.Mean dependent var755.1222Adjusted R-squared0.S.D. dependent var258.7206S.E. of regression60.82273Akaike info criterion11.20482Sum squared resid55491.07Schwarz criterion11.35321Log likelihood-97.84334Hannan-Quinn criter.11.22528F-statistic146.2974Durbin-Watson stat2.Prob(F-sta

30、tistic)0.模型为：Y = 0.X + 52.37031T-50.01638对模型进行检验：1）可决系数是0.，修正的可决系数为0.，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.，10.06702，均大于t（15）=2.131，所以这些系数都是显著的。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.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：Dependent Variable: YMethod: Least SquaresDate: 12/

31、01/14 Time: 22:30Sample: 1 18Included observations: 18VariableCoefficientStd. Errort-StatisticProb.T63.016764.13.854160.0000C-11.5817158.02290-0.0.8443R-squared0.Mean dependent var755.1222Adjusted R-squared0.S.D. dependent var258.7206S.E. of regression73.97565Akaike info criterion11.54979Sum squared

32、 resid87558.36Schwarz criterion11.64872Log likelihood-101.9481Hannan-Quinn criter.11.56343F-statistic191.9377Durbin-Watson stat2.Prob(F-statistic)0.Dependent Variable: XMethod: Least SquaresDate: 12/01/14 Time: 22:34Sample: 1 18Included observations: 18VariableCoefficientStd. Errort-StatisticProb.T1

33、23.151631.841503.0.0014C444.5888406.17861.0.2899R-squared0.Mean dependent var1942.933Adjusted R-squared0.S.D. dependent var698.8325S.E. of regression517.8529Akaike info criterion15.44170Sum squared resid.Schwarz criterion15.54063Log likelihood-136.9753Hannan-Quinn criter.15.45534F-statistic14.95867D

34、urbin-Watson stat1.Prob(F-statistic)0.以上分别是y与T，X与T的一元回归模型分别是：Y = 63.01676T - 11.58171X = 123.1516T + 444.5888（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: 18VariableCoefficientStd. Errort-StatisticProb.E20.0.3.0.007

35、8C3.96E-1413.880832.85E-151.0000R-squared0.Mean dependent var2.30E-14Adjusted R-squared0.S.D. dependent var71.76693S.E. of regression58.89136Akaike info criterion11.09370Sum squared resid55491.07Schwarz criterion11.19264Log likelihood-97.84334Hannan-Quinn criter.11.10735F-statistic9.Durbin-Watson stat2.Prob(F-statistic)0.模型为：E1 = 0.E2 + 3.96e-14参数：斜率系数为0.，截距为3.96e-14（3）由上可知，2与2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，它们的变化规律是一致的。3.6（1）预期的符号是X1，X2,X3,X4,X5的符号为正，X6的符号为负（2）根据Eviews分析得到数据如下：Dependent Variable: YMethod: Lea