Project

Only available on StudyMode
  • Download(s) : 50
  • Published : January 3, 2013
Open Document
Text Preview
ECONOMETRICS 1
SUMMATIVE PROJECT

Introduction.
“There's nothing in the world so demoralizing as money.” Sophocles, Antigone

Nowadays, a lot of people have invested in a mutual fund. Because it became more popular. They think that there are low risks and also it is sample type of investment. But probably, mutual funds are not so in a real. In a recent study, Craig MacKinley (1993: p4) argued that One of the important problems of modern financial economics is the quantification of the trade-off between risk and expected return. Although common sense suggests that investments free of risk will generally yield lower returns than riskier investments such as the stock market, it was only with the development of the Sharpe-Lintner capital asset pricing model (CAPM) that economists were able to quantify these differences in returns.

By this research project we will understand how mutual fund manager work with this data. To understand how it works we will use basic CAPM model, after that Fama and French’s (1993) three-factor model and will add two addition factors: momentum factor and traded liquidity. With these models we can make some analyses. We will do analyses to find the significant factors and to check robustness of results against autocorrelation and hetroscedasticity.

MODEL 1 (CAPM).

At the first stage using the mutual fund we will run the CAPM regression and conduct appropriate tests of the CAPM.

Table 1.
| | | | |
| | | | |
Variable| Coefficient| Std. Error| t-Statistic| Prob.  | | | | | |
| | | | |
C| -0.004677| 0.000554| -8.439520| 0.0000|
EXRM| 0.032867| 0.012014| 2.735859| 0.0065|
| | | | |
| | | | |
R-squared| 0.016433|     Mean dependent var| -0.004529| Adjusted R-squared| 0.014237|     S.D. dependent var| 0.011784| S.E. of regression| 0.011700|     Akaike info criterion| -6.053978| Sum squared resid| 0.061329|     Schwarz criterion| -6.035715| Log likelihood| 1364.145|     Hannan-Quinn criter.| -6.046780| F-statistic| 7.484923|     Durbin-Watson stat| 2.034496| Prob(F-statistic)| 0.006469| | | |

| | | | |
| | | | |

At table 1 we can find that pricing errors (αi) is negative, it is mean that mutual fund manager’s derelict their work, they show that investment portfolio with negative yield. They chose wrong shares. The significant factors of this model are alpha and beta. Table 2.

Heteroskedasticity Test: White| |
| | | | |
| | | | |
F-statistic| 0.633748|     Prob. F(2,447)| 0.5311|
Obs*R-squared| 1.272394|     Prob. Chi-Square(2)| 0.5293| Scaled explained SS| 1.483602|     Prob. Chi-Square(2)| 0.4763| | | | | |
| | | | |

I checked the robustness of my results for Heteroscedasticity by White test on table 2. As we know White test is a universal procedure of testing heteroscedastisity-consistent standard error from linear regression model. After the testing by White test we see on table 2 that this model is not heteroscedasticity. Model is Homoscedasticy. Table 3.

Dependent Variable: Y| | |
Method: Least Squares| | |
Date: 12/12/12 Time: 19:20| | |
Sample: 1968M02 2005M07| | |
Included observations: 450| | |
White heteroskedasticity-consistent standard errors & covariance| | | | | |
| | | | |
Variable| Coefficient| Std. Error| t-Statistic| Prob.  | | | | | |
| | | | |
C| -0.004677| 0.000552| -8.477641| 0.0000|
EXRM| 0.032867| 0.012580| 2.612656| 0.0093|
| | | | |
| | | | |
R-squared| 0.016433|     Mean dependent var| -0.004529| Adjusted R-squared| 0.014237|     S.D. dependent var| 0.011784| S.E. of regression| 0.011700|     Akaike info criterion| -6.053978| Sum squared resid| 0.061329|     Schwarz criterion| -6.035715| Log likelihood| 1364.145|     Hannan-Quinn criter.| -6.046780| F-statistic| 7.484923|...
tracking img