1、计量经济学上机作业试题以及答案题目：第一题：根据下列数据建模并估计结果，并力求使得拟合效果最好。YX1X217.212.50.10718.8513.70.10516.7111.30.10414.8110.40.10219.0214.20.10120.5515.20.09324.2917.10.09124.3816.90.13027.817.20.11043.0118.460.09365.6519.90.10267.0520.30.11588.2521.50.10178.1520.90.10491.48522.110.102110.323.80.098第二题：下表中，Y代表新客车出售量，X1代表
2、新车价格指数，X2代表消费者价格指数，X3代表个人可支配收入，X4代表利率，X5代表就业人数。试建模并估计结果。年度YX1X2X3X4X5197110227112121.3776.84.8979367197210872111125.3839.64.5582153197311350111.1133.1949.87.388506419748775117.5147.71038.48.618679419758539127.6161.21142.86.168584619769994135.7170.51252.65.2288752197711046142.9181.51379.35.5920171978
3、11164153.8195.31551.27.7896048197910559166217.71729.310.259882419808979179.3247191811.289930319818535190.2272.32127.613.7319827980197.6286.62261.411.29952619839179202.6297.42428.18.69198410394208.5307.62670.69.65198511039215.2318.52841.17.75198611450224.4323.43022.16.31第三题为了了解影响电信业务的发展情况，特收集了如下数据，请建
4、模并估计合理的结果。 年电信业务总量邮政业务总量中国人口数市镇人口比重人均GDP人均消费水平19911.51630.527511.58230.26371.8790.89619922.26570.636711.71710.27632.2871.07019933.82450.802611.85170.28142.9391.33119945.92300.958911.98500.28623.9231.74619958.75511.133412.11210.29044.8542.236199612.08751.332912.23890.29375.5762.641199712.68951.443412
5、.36260.29926.0532.834199822.64941.662812.48100.30406.3072.972199931.32381.984412.59090.30896.5343.143第四题：X代表职工的工龄，Y代表薪水。要求：1. 通过散点图或残差图对样本进行初步观察。2. 对可能存在的问题进行检验。3. 采取措施消除问题。4. 写出最终表达式。XY0.5690002.5705004.5740506.5826008.59143910.58312712.58470014.58260116.59328618.59040020.598200232699662303485200第五
6、题：处于研究的目的，现需要了解A和B两个经济变量的联系，但是没有先验信息提示A和B的关系，请根据所学知识进行处理。AB36.9952.80533.655.90635.4263.02742.3572.93152.4884.7953.6686.58958.5398.79767.48113.20178.13126.90595.13143.936112.6154.391128.68168.129123.97163.351117.35172.547139.61190.682152.88194.538137.95194.657141.06206.326163.45223.541183.8232.72419
7、2.61239.459182.81235.142第六题下列数据中，X表示家庭收入，Y表示家庭支出，请对如下数据运用戈德菲尔德-匡特检验。XY8055100658570110801207911584130981409512590907510574160110150113165125145108180115225140200120240145185130220152210144245175260180190135205140265178270191230137250189第七题：下表中，C代表某年度美国国内平均铜价，G代表年度GNP，I代表年度平均工业生产指数，L代表年度平均伦敦金属交易所铜价，H
8、代表新房动工数，A代表年度平均铝价。要求：试建立模型拟合美国铜价的变化（提示：消除自相关问题），并比较自相关问题解决前后回归估计的结果。年度CGILHAYX1X2X3X4X5195121.89330.245.1220.4149119195222.29347.250.9259.5150419.41195319.63366.153.3256.3143820.93195422.85366.353.6249.3155121.78195533.77399.354.6352.3164623.68195639.18420.761.1329.1134926.01195730.5844261.9219.6122
9、427.52195826.344757.9234.8138226.89195930.748364.8237.41553.726.85196032.150666.2245.81296.127.23196130523.366.7229.2136525.46196230.8563.872.2233.91492.523.88196330.8594.776.5234.21634.922.62196432.6635.781.7347156123.72196535.4688.189.8468.11509.724.5196636.675397.85551195.824.5196738.6796.3100418
10、1321.924.98196842.2868.5106.3525.21545.425.58196947.9935.5111.1620.71499.527.18197058.2982.4107.8588.6146928.721971521063.4109.6444.42084.529197251.21171.1119.7427.82378.526.67197359.51306.6129.8727.12057.525.33197477.31412.9129.3877.61352.534.06197564.21528.8117.8556.61171.439.79197669.61700.1129.8
11、780.61547.644.49197766.81887.2137.1750.71989.851.23197866.52127.6145.2709.82023.354.42197998.32628.8152.5935.71749.261.011980101.42633.1147.1940.91298.570.87参考答案：（本人自己做的，只供参考）姓名：徐任学号：专业：数经班第一题解：先对原使数据建立模型：Y=C(1)*X1+C(2)*X2+C(3),具体回归分析结果（结果一）：Dependent Variable: YMethod: Least SquaresDate: 12/24/10 T
12、ime: 14:49Sample: 1 16Included observations: 16Y=C(1)*X1+C(2)*X2+C(3)CoefficientStd. Errort-StatisticProb.C(1)7.0.8.0.0000C(2)-199.9262378.0811-0.0.6059C(3)-60.3090142.76070-1.0.1819R-squared0.Mean dependent var45.46906Adjusted R-squared0.S.D. dependent var32.55622S.E. of regression13.70940Akaike in
13、fo criterion8.Sum squared resid2443.321Schwarz criterion8.Log likelihood-62.93121Durbin-Watson stat0.但是，这里存在这很多问题。首先，考虑到Y，X1，X2的Correlation Matrix：X1X2YX11.-0.0.X2-0.1.-0.Y0.-0.1.注意到Y与X2的相关系数仅为-0.，故X2对Y的解释能力有限，应当去除。以下，仅考虑X1对Y的影响。先建立模型：Y=C(1)*X1+C(2)，具体回归分析结果（结果二）：Dependent Variable: YMethod: Least S
14、quaresDate: 12/24/10 Time: 15:30Sample: 1 16Included observations: 16Y=C(1)*X1+C(2)CoefficientStd. Errort-StatisticProb.C(1)7.0.8.0.0000C(2)-81.4012015.00815-5.0.0001R-squared0.Mean dependent var45.46906Adjusted R-squared0.S.D. dependent var32.55622S.E. of regression13.35203Akaike info criterion8.Su
15、m squared resid2495.875Schwarz criterion8.Log likelihood-63.10146Durbin-Watson stat0.经过改良后的结果尽管X1的t值很高，即其解释能力很强，但是对于随机项才C（2），其t值居然为-5.，这让我们不得不怀疑是否存在其他解释变量，对Y有明显影响考虑Y与X1的散点图：注意到，Y相对于X1的 并不是以一个恒定速率增大，而是存在着一个拐点，在拐点之前，Y增大速率较平缓，而在拐点之后，Y增大的速率明显变快。且拐点可从上图中其值在17左右，不妨设立虚拟变量， 新的数据具体如下：YX1Di17.212.5018.8513.70
16、16.7111.3014.8110.4019.0214.2020.5515.2024.2917.1024.3816.9027.817.2143.0118.46165.6519.9167.0520.3188.2521.5178.1520.9191.48522.111110.323.81现在建立模型：Y=C(1)*X1+C(2)*DI+C(3)其具体回归分析结果（结果三）：Dependent Variable: YMethod: Least SquaresDate: 12/24/10 Time: 16:41Sample: 1 16Included observations: 16Y=C(1)*X1
17、+C(2)*DI+C(3)CoefficientStd. Errort-StatisticProb.C(1)6.1.3.0.0018C(2)11.2463812.431360.0.3821C(3)-66.2865322.52412-2.0.0114R-squared0.Mean dependent var45.46906Adjusted R-squared0.S.D. dependent var32.55622S.E. of regression13.43946Akaike info criterion8.Sum squared resid2348.049Schwarz criterion8.
18、Log likelihood-62.61303Durbin-Watson stat0.虽然已经加入了虚拟变量，但是仍然存在着两点问题：一，C（3）的 t 值仅为-2.，不够显著二，值仅为0.，表示模型的解释能力不够显著现对模型进行修正：Y=C(1)*X1+C(2)*DI+C(3)*DI*X1+C(4)其具体回归分析结果（结果四）：Dependent Variable: YMethod: Least SquaresDate: 12/24/10 Time: 16:44Sample: 1 16Included observations: 16Y=C(1)*X1+C(2)*DI+C(3)*DI*X1+
19、C(4)CoefficientStd. Errort-StatisticProb.C(1)1.0.4.0.0007C(2)-192.24188.-22.370190.0000C(3)11.455160.24.235260.0000C(4)0.4.0.0.9624R-squared0.Mean dependent var45.46906Adjusted R-squared0.S.D. dependent var32.55622S.E. of regression1.Akaike info criterion4.Sum squared resid47.01208Schwarz criterion4
20、.Log likelihood-31.32554Durbin-Watson stat1.故：Y=1.X1-192.2418DI+11.4551DI*X1+0.第二题解：建立模型：Y=C(1)*X1+C(2)*X2+C(3)*X3+C(4)*X4+C(5)*X5+C(6)其具体回归分析结果（结果一）：Dependent Variable: YMethod: Least SquaresDate: 12/24/10 Time: 17:22Sample: 1 16Included observations: 16Y=C(1)*X1+C(2)*X2+C(3)*X3+C(4)*X4+C(5)*X5+C(6
21、)CoefficientStd. Errort-StatisticProb.C(1)50.5377669.700810.0.4850C(2)-103.504251.14744-2.0.0705C(3)6.3.1.0.1306C(4)-105.9787151.9428-0.0.5014C(5)0.0.1.0.3367C(6)2933.9068172.2570.0.7271R-squared0.Mean dependent var10005.13Adjusted R-squared0.S.D. dependent var1163.645S.E. of regression706.1345Akaik
22、e info criterion16.23749Sum squared resid.Schwarz criterion16.52721Log likelihood-123.8999Durbin-Watson stat1.X1X2X3X4X5YX11.0.0.0.0.-0.X20.1.0.0.0.-0.X30.0.1.0.0.0.X40.0.0.1.0.-0.X50.0.0.0.1.0.Y-0.-0.0.-0.0.1.观察到X5与X1,X5与X2,X5与X3的相关系数分别为0. ，0. ，0.。均接近一，而X3与X1，X3与X2的相关系数为0. ，0.也接近一，即存在着多重共线性问题。为去除多重共线性，进行逐步回归。分别作Y与X1，X2，X3，X4，X5间的回归：以下是具体回归结果：（结果二、1）：Dependent Variable: YMethod: Least SquaresDate: 12/25/10 Time: 22:47Sample: 1 16Included observations: 16Y=C(1)*X1+C(2)CoefficientStd. Errort-StatisticProb.C(1)-1.7.-0.0.8076C(2)10311.801271.7028.0.0000R-squared0.Mean dependent var10005.13Ad
