李子奈版-计量经济学课后作业三

李子奈版-计量经济学课后作业三 计量经济学 综合练习三 2000年中国部分省市城镇居民每个家庭平均全年可支配收入(X)与消费性支出 (Y)的统计数据如下表: 地区 可支配收入(X) 消费性支出(Y) 1 10349.69 8493.49 2 8140.5 6121.04 3 5129.05 3927.75 4 5357.79 4356.06 5 4810 4020.87 6 4912.88 3824.44 7 11718.01 8868.19 8 6800.23 5323.18 9 9279.16 7020.22 10 6489.97 5022 11 5661.16 4348.47 12 4724.11 3941.87 13 4766.26 3830.71 14 5524.54 4644.5 15 6218.73 5218.79 16 9761.57 8016.91 17 5124.24 4276.67 18 4916.25 4126.47 19 5169.96 4185.73 20 5644.86 4422.93 1、用OLS估计法估计参数 设模型为: Y,,，,X，, 12 运行EVIEWS软件，并输入数据，得计算结果如下: Dependent Variable: Y Method: Least Squares Date: 06/09/09 Time: 19:27 Sample: 1 20 Included observations: 20 Variable Coefficient Std. Error t-Statistic Prob. C 272.3635 159.6773 1.705713 0.1053 X 0.755125 0.023316 32.38690 0.0000 R-squared 0.983129 Mean dependent var 5199.515 Adjusted R-squared 0.982192 S.D. dependent var 1625.275 S.E. of regression 216.8900 Akaike info criterion 13.69130 Sum squared resid 846743.0 Schwarz criterion 13.79087 Log likelihood -134.9130 F-statistic 1048.912 Durbin-Watson stat 1.189253 Prob(F-statistic) 0.000000 2、异方差检验 (1)Goldfeld-Quandt检验 在workfile窗口Procs菜单项选Sort series项，出现排序对话框，输入X， OK。 在Sample菜单里，定义为1-8项，用OLS 方法 快递客服问题件处理详细方法山木方法pdf计算方法pdf华与华方法下载八字理论方法下载 计算得如下结果: Y = 1277.161 + 0.554126*X (0.829000) (1.779287) R-squared,0.345397 Sum squared resid1,126528.3 Dependent Variable: Y Method: Least Squares Date: 06/10/09 Time: 15:53 Sample: 1 8 Included observations: 8 Variable Coefficient Std. Error t-Statistic Prob. C 1277.161 1540.604 0.829000 0.4388 X 0.554126 0.311432 1.779287 0.1255 R-squared 0.345397 Mean dependent var 4016.814 Adjusted R-squared 0.236296 S.D. dependent var 166.1712 S.E. of regression 145.2172 Akaike info criterion 13.00666 Sum squared resid 126528.3 Schwarz criterion 13.02652 Log likelihood -50.02663 F-statistic 3.165861 Durbin-Watson stat 3.004532 Prob(F-statistic) 0.125501 在Sample菜单里，定义为13-20项，用OLS方法计算得如下结果: Y = 212.2118 + 0.761893*X (0.399729) (12.62505) R-squared,0.963723 Sum squared resid2,615472.0 Dependent Variable: Y Method: Least Squares Date: 06/10/09 Time: 15:58 Sample: 13 20 Included observations: 8 Variable Coefficient Std. Error t-Statistic Prob. C 212.2118 530.8892 0.399729 0.7032 X 0.761893 0.060348 12.62505 0.0000 R-squared 0.963723 Mean dependent var 6760.477 Adjusted R-squared 0.957676 S.D. dependent var 1556.814 S.E. of regression 320.2790 Akaike info criterion 14.58858 Sum squared resid 615472.0 Schwarz criterion 14.60844 Log likelihood -56.35432 F-statistic 159.3919 Durbin-Watson stat 1.722960 Prob(F-statistic) 0.000015 2e615472,2F,,,4.8643求F统计量:，查F分布表，给定显著性水平2126528.3e,1 ,,0.05F,4.8643F(6,6),4.28F(6,6),4.28，得临界值，比较>，拒绝原0.050.05 22H:,,,假设，表明随机误差项显著的存在异方差。 012 (2)怀特检验 建立如下辅助回归 22 e,,，,X，,X，,012 OLS法的估计结果如下 22ˆ e,,180998.9，49.42846X,0.002115X (1.751858) ( 1.70800) ( -1.144742) 2 R,0.632606 Dependent Variable: E2 Method: Least Squares Date: 06/10/09 Time: 18:11 Sample: 2001 2020 Included observations: 20 Variable Coefficient Std. Error t-Statistic Prob. C -180998.9 103318.2 -1.751858 0.0978 X 49.42846 28.93929 1.708006 0.1058 X2 -0.002115 0.001847 -1.144742 0.2682 R-squared 0.632606 Mean dependent var 42337.15 Adjusted R-squared 0.589384 S.D. dependent var 45279.67 S.E. of regression 29014.92 Akaike info criterion 23.52649 Sum squared resid 1.43E+10 Schwarz criterion 23.67585 Log likelihood -232.2649 F-statistic 14.63595 Durbin-Watson stat 1.061453 Prob(F-statistic) 0.000201 2怀特统计量,该值大于5%显著性水平下自由的为2nR,20*0.632606,12.65212 22,的分布的相应临界值，因此拒绝同方差性的原假设。 ,,5.990.05 3、异方差的修正 WLS估计法 1W,首先生成权函数,然后用OLS估计参数， abs(resid) Y,415.6603，0.729026X (3.5533) (32.5034) 22 F=1056.477 RSS=106856.0 R,0.999889R,0.999 Dependent Variable: Y Method: Least Squares Date: 06/10/09 Time: 16:37 Sample: 2001 2020 Included observations: 20 Weighting series: 1/ABS(E) Variable Coefficient Std. Error t-Statistic Prob. C 415.6603 116.9791 3.553288 0.0023 X 0.729026 0.022429 32.50349 0.0000 Weighted Statistics R-squared 0.999895 Mean dependent var 4471.606 Adjusted R-squared 0.999889 S.D. dependent var 7313.160 S.E. of regression 77.04831 Akaike info criterion 11.62138 Sum squared resid 106856.0 Schwarz criterion 11.72096 Log likelihood -114.2138 F-statistic 1056.477 Durbin-Watson stat 1.622495 Prob(F-statistic) 0.000000 Unweighted Statistics R-squared 0.981664 Mean dependent var 5199.515 Adjusted R-squared 0.980645 S.D. dependent var 1625.275 S.E. of regression 226.1101 Sum squared resid 920263.9 Durbin-Watson stat 1.223519