证券投资分析作业
CAPM模型在中国资本市场的有效性检验
1、数据选取
此次实验主要考察CAPM模型在中国电力行业是否适用，因此随机抽取了电力行业的十只股票（时间段为2010年1月1日—2010年12月31日），分别为
股票代码 002039 600116 600310 600505 600674
股票简称 黔源电力 三峡水利 桂东电力 西昌电力 川投能源 股票代码 600101 600292 600452 600644 600969 股票简称 明星电力 九龙电力 涪陵电力 乐山电力 郴电国际 选取沪深300指数为综合指数，选取2010年的国债的利率作为无风险资产的收益率（0.025）。 2、β系数的确定
CAPM模型中，β系数可以表述为：Ri – Rf =αi + βi( Rm - Rf) + εi，其中Ri为每一种证券的收益率，Rf为无风险收益率，Rm为市场收益率。
使用Eviews软件对每只股票每日风险溢价与市场组合风险溢价进行回归，得到每只股票的β值。如下：
（1）黔源电力
Dependent Variable: Y Method: Least Squares Date: 12/26/11 Time: 16:35 Sample: 1 241 Included observations: 241
Variable Coefficient Std. Error t-Statistic
C -0.008685 0.002294 -3.786006 X 0.616613 0.076324 8.078883
R-squared 0.214509 Mean dependent var Adjusted R-squared 0.211223 S.D. dependent var S.E. of regression 0.018838 Akaike info criterion Sum squared resid 0.084811 Schwarz criterion Log likelihood 616.2670 F-statistic Durbin-Watson stat 1.914885 Prob(F-statistic)
Prob.
0.0002 0.0000
-0.024413 0.021210 -5.097652 -5.068732 65.26835 0.000000
（2）明星电力
Dependent Variable: Y2 Method: Least Squares Date: 12/26/11 Time: 16:46 Sample: 1 241 Included observations: 241
Variable Coefficient Std. Error t-Statistic
C -0.032526 0.007661 -4.245595 X -0.215975 0.254892 -0.847320
R-squared 0.002995 Mean dependent var Adjusted R-squared -0.001177 S.D. dependent var S.E. of regression 0.062910 Akaike info criterion Sum squared resid 0.945894 Schwarz criterion Log likelihood 325.6566 F-statistic Durbin-Watson stat 1.196603 Prob(F-statistic)
Prob.
0.0000 0.3977
-0.027017 0.062873 -2.685947 -2.657027 0.717951 0.397665
（3）三峡水利
Dependent Variable: Y3 Method: Least Squares Date: 12/26/11 Time: 16:48 Sample: 1 241 Included observations: 241
Variable Coefficient Std. Error t-Statistic
C -0.029398 0.004289 -6.853614 X -0.160104 0.142712 -1.121869
R-squared 0.005238 Mean dependent var Adjusted R-squared 0.001076 S.D. dependent var S.E. of regression 0.035223 Akaike info criterion Sum squared resid 0.296518 Schwarz criterion Log likelihood 465.4395 F-statistic Durbin-Watson stat 1.523152 Prob(F-statistic)
Prob.
0.0000 0.2630
-0.025314 0.035242 -3.845971 -3.817051 1.258591 0.263044
（4）九龙电力
Dependent Variable: Y4 Method: Least Squares
Date: 12/26/11 Time: 16:50 Sample: 1 241
Included observations: 241
Variable
C X
R-squared
Adjusted R-squared S.E. of regression Sum squared resid Log likelihood
Durbin-Watson stat
Coefficient Std. Error t-Statistic
-0.023708 0.004362 -5.434675 -0.003584 0.145136 -0.024693
0.000003 Mean dependent var -0.004182 S.D. dependent var 0.035821 Akaike info criterion 0.306677 Schwarz criterion 461.3801 F-statistic
1.598474 Prob(F-statistic)
Prob.
0.0000 0.9803
-0.023616 0.035747 -3.812283 -3.783363 0.000610 0.980321
（5）桂东电力
Dependent Variable: Y5 Method: Least Squares Date: 12/26/11 Time: 16:52 Sample: 1 241 Included observations: 241
Variable Coefficient Std. Error t-Statistic
C -0.027401 0.003728 -7.351010 X -0.174539 0.124019 -1.407360
R-squared 0.008219 Mean dependent var Adjusted R-squared 0.004069 S.D. dependent var S.E. of regression 0.030609 Akaike info criterion Sum squared resid 0.223927 Schwarz criterion Log likelihood 499.2743 F-statistic Durbin-Watson stat 1.567083 Prob(F-statistic)
Prob.
0.0000 0.1606
-0.022949 0.030672 -4.126758 -4.097838 1.980662 0.160620
（6）涪陵电力
Dependent Variable: Y6 Method: Least Squares Date: 12/26/11 Time: 16:53 Sample: 1 241 Included observations: 241
Variable Coefficient Std. Error t-Statistic
C -0.027569 0.009995 -2.758287 X 0.028673 0.332537 0.086226
R-squared 0.000031 Mean dependent var Adjusted R-squared -0.004153 S.D. dependent var S.E. of regression 0.082074 Akaike info criterion Sum squared resid 1.609937 Schwarz criterion
Prob.
0.0063 0.9314
-0.028300 0.081904 -2.154127 -2.125208
Log likelihood
Durbin-Watson stat
261.5723 F-statistic
1.109620 Prob(F-statistic)
0.007435
0.931359
（7）西昌电力
Dependent Variable: Y7 Method: Least Squares Date: 12/26/11 Time: 16:55 Sample: 1 241 Included observations: 241
Variable Coefficient Std. Error t-Statistic
C -0.026434 0.004241 -6.233043 X 0.016241 0.141098 0.115107
R-squared 0.000055 Mean dependent var Adjusted R-squared -0.004128 S.D. dependent var S.E. of regression 0.034825 Akaike info criterion Sum squared resid 0.289849 Schwarz criterion Log likelihood 468.1804 F-statistic Durbin-Watson stat 1.452457 Prob(F-statistic)
Prob.
0.0000 0.9085
-0.026848 0.034753 -3.868717 -3.839798 0.013250 0.908457
（8）乐山电力
Dependent Variable: Y8 Method: Least Squares Date: 12/26/11 Time: 16:56 Sample: 1 241 Included observations: 241
Variable Coefficient Std. Error t-Statistic
C -0.028174 0.003964 -7.107256 X -0.171916 0.131888 -1.303503
R-squared 0.007059 Mean dependent var Adjusted R-squared 0.002905 S.D. dependent var S.E. of regression 0.032552 Akaike info criterion Sum squared resid 0.253245 Schwarz criterion Log likelihood 484.4484 F-statistic Durbin-Watson stat 1.733619 Prob(F-statistic)
Prob.
0.0000 0.1937
-0.023789 0.032599 -4.003721 -3.974802 1.699119 0.193657
（9）川投能源
Dependent Variable: Y9 Method: Least Squares
Date: 12/26/11 Time: 16:58 Sample: 1 241
Included observations: 241
Variable
C X
R-squared
Adjusted R-squared S.E. of regression Sum squared resid Log likelihood
Durbin-Watson stat
Coefficient Std. Error t-Statistic
-0.028579 0.003039 -9.402725 -0.144156 0.101126 -1.425514
0.008431 Mean dependent var 0.004282 S.D. dependent var 0.024959 Akaike info criterion 0.148885 Schwarz criterion 548.4558 F-statistic
1.710352 Prob(F-statistic)
Prob.
0.0000 0.1553
-0.024902 0.025013 -4.534903 -4.505984 2.032090 0.155313
（10）郴电国际
Dependent Variable: Y10 Method: Least Squares Date: 12/26/11 Time: 16:59 Sample: 1 241 Included observations: 241
Variable Coefficient Std. Error t-Statistic
C -0.022969 0.003915 -5.866217 X 0.072408 0.130268 0.555835
R-squared 0.001291 Mean dependent var Adjusted R-squared -0.002888 S.D. dependent var S.E. of regression 0.032152 Akaike info criterion Sum squared resid 0.247062 Schwarz criterion Log likelihood 487.4270 F-statistic Durbin-Watson stat 1.756510 Prob(F-statistic)
Prob.
0.0000 0.5788
-0.024816 0.032105 -4.028440 -3.999520 0.308952 0.578844
3、用求出的10只股票的β值与十只股票的平均收益率进行回归，如下：
Dependent Variable: YY Method: Least Squares
Date: 12/26/11 Time: 17:27 Sample: 1 10
Included observations: 10
Variable Coefficient
C -5.47E-05 XX 1.30E-05
t-Statistic
-0.090685 0.005022
Prob.
0.9300 0.9961
Std. Error
0.000603 0.002598
R-squared
Adjusted R-squared S.E. of regression Sum squared resid Log likelihood
Durbin-Watson stat
0.000003 Mean dependent var -0.124996 S.D. dependent var 0.001905 Akaike info criterion 2.90E-05 Schwarz criterion 49.55942 F-statistic
2.042840 Prob(F-statistic)
-5.49E-05
0.001796 -9.511885 -9.451368 2.52E-05 0.996116
即样本回归方程为
Yt = -5.47 E-05 + 1.30 E-05 +εi 4、统计检验
r2 = 0.000003，说明仅有总离差平方和的0.003%被样本回归直线解释，回归直线对样本点的拟合优度非常低。
给出显著性水平α=0.05，P>α，t检验不能通过；F检验也不能通过。 从以上的检验可以看出，此模型没有通过各种检验，拟合不好，不能代表x与y的关系。 5、结论
通过分析可以看出，CAPM模型对我国资本市场上的电力行业不适用，通过更多的分析可以得出，CAPM模型对我国资本市场是无效的。
我国资本市场是政策导向型市场，采用核准制度，是计划经济的产物，资本市场还没有实现市场完全控制，资本未达到自由流动，还存在信息不对称、经济发展程度落后于发达国家、国际金融环境恶化等现象，加之CAPM模型的假设条件比较苛刻，因此在中国资本市场上应用这一模型极为困难。
因篇幅问题不能全部显示，请点此查看更多更全内容