1、 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: 12/23/15 Time: 14:37Sample: 1 22Included observations: 22Variable Coefficient Std. Error t-Statistic Prob. C 56.64794 1.960820 28.88992 0.0000X1 0.128360 0.027242 4.711834 0.0001R-squared 0.526082
2、Mean dependent var 62.50000Adjusted R-squared 0.502386 S.D. dependent var 10.08889S.E. of regression 7.116881 Akaike info criterion 6.849324Sum squared resid 1013.000 Schwarz criterion 6.948510Log likelihood -73.34257 Hannan-Quinn criter. 6.872689F-statistic 22.20138 Durbin-Watson stat 0.629074Prob(
3、F-statistic) 0.000134有上可知,关系式为 y=56.64794+0.128360x1关于人均寿命与成人识字率的关系,用 Eviews 分析如下:Dependent Variable: YMethod: Least SquaresDate: 12/23/15 Time: 15:01Sample: 1 22Included observations: 22Variable Coefficient Std. Error t-Statistic Prob. C 38.79424 3.532079 10.98340 0.0000X2 0.331971 0.046656 7.11530
4、8 0.0000R-squared 0.716825 Mean dependent var 62.50000Adjusted R-squared 0.702666 S.D. dependent var 10.08889S.E. of regression 5.501306 Akaike info criterion 6.334356Sum squared resid 605.2873 Schwarz criterion 6.433542Log likelihood -67.67792 Hannan-Quinn criter. 6.357721F-statistic 50.62761 Durbi
5、n-Watson stat 1.846406Prob(F-statistic) 0.000001由上可知,关系式为 y=38.79424+0.331971x2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: 12/23/14 Time: 15:20Sample: 1 22Included observations: 22Variable Coefficient Std. Error t-Statistic Prob. C 31.79956 6.536434 4.864971 0.0
6、001X3 0.387276 0.080260 4.825285 0.0001R-squared 0.537929 Mean dependent var 62.50000Adjusted R-squared 0.514825 S.D. dependent var 10.08889S.E. of regression 7.027364 Akaike info criterion 6.824009Sum squared resid 987.6770 Schwarz criterion 6.923194Log likelihood -73.06409 Hannan-Quinn criter. 6.8
7、47374F-statistic 23.28338 Durbin-Watson stat 0.952555Prob(F-statistic) 0.000103由上可知,关系式为 y=31.79956+0.387276x3(2 ) 关于人均寿命与人均 GDP 模型,由上可知,可决系数为 0.526082,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)=4.711834t 0.025(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 0.716825,说明所建模型整体上对样本数据拟合较
8、好。对于回归系数的 t 检验:t( 2)=7.115308t 0.025(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 0.537929,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)=4.825285t 0.025(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
9、: 12/23/15 Time: 17:46Sample (adjusted): 1 33Included observations: 33 after adjustmentsVariable Coefficient Std. Error t-Statistic Prob. X 0.176124 0.004072 43.25639 0.0000C -154.3063 39.08196 -3.948274 0.0004R-squared 0.983702 Mean dependent var 902.5148Adjusted R-squared 0.983177 S.D. dependent v
10、ar 1351.009S.E. of regression 175.2325 Akaike info criterion 13.22880Sum squared resid 951899.7 Schwarz criterion 13.31949Log likelihood -216.2751 Hannan-Quinn criter. 13.25931F-statistic 1871.115 Durbin-Watson stat 0.100021Prob(F-statistic) 0.000000由上可知,模型的参数:斜率系数 0.176124,截距为154.3063关于浙江省财政预算收入与全省
11、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)对于回归系数的 t 检验: t(2 )=43.25639t 0.025(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=0.176124X154.3063(0.004072) (39.08196)t= (43.25639) (-3.948274)R2=0.983702 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 0.176124 亿元。(2)当 x=32000 时,
12、进行点预测,由上可知 Y=0.176124X154.3063,代入可得:Y= Y=0.176124*32000154.3063=5481.6617进行区间预测:先由 Eviews 分析:X YMean 6000.441 902.5148Median 2689.280 209.3900Maximum 27722.31 4895.410Minimum 123.7200 25.87000Std. Dev. 7608.021 1351.009Skewness 1.432519 1.663108Kurtosis 4.010515 4.590432Jarque-Bera 12.69068 18.69063
13、Probability 0.001755 0.000087Sum 198014.5 29782.99Sum Sq. Dev. 1.85E+09 58407195Observations 33 33由上表可知,x2=(X iX) 2=2x(n1)= 7608.0212 x (331)=1852223.473(XfX)2=(32000 6000.441)2=675977068.2当 Xf=32000 时,将相关数据代入计算得到:5481.66172.0395x175.2325x1/33+1852223.473/675977068.2Yf5481.6617+2.0395x175.2325x1/33+
14、1852223.473/675977068.2即 Yf 的置信区间为(5481.6617 64.9649, 5481.6617+64.9649)(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: 12/23/15 Time: 18:04Sample (adjusted): 1 33Included observations: 33 after adjustmentsVariable Coefficient Std. Error t-Statistic Prob
15、. LNX 0.980275 0.034296 28.58268 0.0000C -1.918289 0.268213 -7.152121 0.0000R-squared 0.963442 Mean dependent var 5.573120Adjusted R-squared 0.962263 S.D. dependent var 1.684189S.E. of regression 0.327172 Akaike info criterion 0.662028Sum squared resid 3.318281 Schwarz criterion 0.752726Log likeliho
16、od -8.923468 Hannan-Quinn criter. 0.692545F-statistic 816.9699 Durbin-Watson stat 0.096208Prob(F-statistic) 0.000000模型方程为:lnY=0.980275lnX-1.918289由上可知,模型的参数:斜率系数为 0.980275,截距为-1.918289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)对于回归系数的 t 检验: t( 2)= 28.58268t0.025(31)=2.0395,对斜
17、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 0.980275%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: 12/23/15 Time: 20:11Sample: 1 12Included observations: 12Variable Coefficient Std. Error t-Statistic Prob. X -64.18400 4.809828 -13.34434 0.0000C
18、 1845.475 19.26446 95.79688 0.0000R-squared 0.946829 Mean dependent var 1619.333Adjusted R-squared 0.941512 S.D. dependent var 131.2252S.E. of regression 31.73600 Akaike info criterion 9.903792Sum squared resid 10071.74 Schwarz criterion 9.984610Log likelihood -57.42275 Hannan-Quinn criter. 9.873871
19、F-statistic 178.0715 Durbin-Watson stat 1.172407Prob(F-statistic) 0.000000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:Y XMean 1619.333 3.523333Median 1630.000 3.715000Maximum 1860.00
20、0 6.230000Minimum 1419.000 0.600000Std. Dev. 131.2252 1.989419Skewness 0.003403 -0.060130Kurtosis 2.346511 1.664917Jarque-Bera 0.213547 0.898454Probability 0.898729 0.638121Sum 19432.00 42.28000Sum Sq. Dev. 189420.7 43.53567Observations 12 12由上表可知,x2=(X iX) 2=2x(n1)= 1.9894192 x (121)=43.5357(XfX)2=
21、(4.5 3.523333)2=0.95387843当 Xf=4.5 时,将相关数据代入计算得到:1556.6472.228x31.73600x1/12+43.5357/0.95387843Yf1556.647+2.228x31.73600x1/12+43.5357/0.95387843即 Yf 的置信区间为(1556.647 478.1231, 1556.647+478.1231)3.1(1)对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: 12/23/15 Time: 20:59
22、Sample: 1 31Included observations: 31Variable Coefficient Std. Error t-Statistic Prob. X2 5.996865 1.406058 4.265020 0.0002X3 -0.524027 0.179280 -2.922950 0.0069X4 -2.265680 0.518837 -4.366842 0.0002C 246.8540 51.97500 4.749476 0.0001R-squared 0.666062 Mean dependent var 16.77355Adjusted R-squared 0
23、.628957 S.D. dependent var 8.252535S.E. of regression 5.026889 Akaike info criterion 6.187394Sum squared resid 682.2795 Schwarz criterion 6.372424Log likelihood -91.90460 Hannan-Quinn criter. 6.247709F-statistic 17.95108 Durbin-Watson stat 1.147253Prob(F-statistic) 0.000001得到模型得:Y=246.8540+5.996865X
24、2- 0.524027 X3-2.265680 X4对模型进行检验:1) 可决系数是 0.666062,修正的可决系数为 0.628957,说明模型对样本拟合较好2) F 检验, F=17.95108F(3,27)=3.65 ,回归方程显著。3) t 检验,t 统计量分别为 4.749476,4.265020,-2.922950,-4.366842,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
25、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 5.996865 辆,城镇人口比重增加个百分点,百户拥有家用汽车减少 0.524027 辆,交通工具消费价格指数每上升,百户拥有家用汽车减少 2.265680 辆。(3 )用 EViews 分析得:Dependent Variable: YMethod: Least SquaresDate: 12/23/15 Time: 21:09Sample: 1 31Included observations: 31Variable Coefficient Std. Er
26、ror t-Statistic Prob. X2 5.135670 1.010270 5.083465 0.0000LNX3 -22.81005 6.771820 -3.368378 0.0023LNX4 -230.8481 49.46791 -4.666624 0.0001C 1148.758 228.2917 5.031974 0.0000R-squared 0.691952 Mean dependent var 16.77355Adjusted R-squared 0.657725 S.D. dependent var 8.252535S.E. of regression 4.82808
27、8 Akaike info criterion 6.106692Sum squared resid 629.3818 Schwarz criterion 6.291723Log likelihood -90.65373 Hannan-Quinn criter. 6.167008F-statistic 20.21624 Durbin-Watson stat 1.150090Prob(F-statistic) 0.000000模型方程为:Y=5.135670 X2-22.81005 LNX3-230.8481 LNX4+1148.758此分析得出的可决系数为 0.6919520.666062,拟合
28、程度得到了提高,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: 12/24/15 Time: 08:23Sample: 1994 2011Included observations: 18Variable Coefficient Std. Error t-Statistic Prob. X2 0.135474 0.012799 10.58454 0.0000X3 18.85348 9.776181 1.928512 0.0729C -18231.58 8638.21
29、6 -2.110573 0.0520R-squared 0.985838 Mean dependent var 6619.191Adjusted R-squared 0.983950 S.D. dependent var 5767.152S.E. of regression 730.6306 Akaike info criterion 16.17670Sum squared resid 8007316. Schwarz criterion 16.32510Log likelihood -142.5903 Hannan-Quinn criter. 16.19717F-statistic 522.
30、0976 Durbin-Watson stat 1.173432Prob(F-statistic) 0.000000由上可知,模型为:Y = 0.135474X2 + 18.85348X3 - 18231.58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=522.0976F ( 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 1.928512,小于 t(15)=2.131,说明
31、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: 12/24/15 Time: 08:47Sample: 1994 2011Included observations: 18Variable Coefficient Std. Error t-Statistic Prob. LNX2 1.564221 0.088988 17.57789 0.0000LNX3 1.760695 0.682115 2.581229 0.0209C -20.52048 5.432487 -3.77
32、7363 0.0018R-squared 0.986295 Mean dependent var 8.400112Adjusted R-squared 0.984467 S.D. dependent var 0.941530S.E. of regression 0.117343 Akaike info criterion -1.296424Sum squared resid 0.206540 Schwarz criterion -1.148029Log likelihood 14.66782 Hannan-Quinn criter. -1.275962F-statistic 539.7364
33、Durbin-Watson stat 0.686656Prob(F-statistic) 0.000000由上可知,模型为:LNY=-20.52048+1.564221 LNX2+1.760695 LNX3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 0.135474 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%