1) The model has 346 observations (n=346) and 3 independent variables (K=3), 4 if you include the intercept (alpha) term. At a 5% significance level, the lower and upper boundaries for the Durbin-Watson statistic are approximately 1.8074 and 1.8419, respectively. At a 1% significance level, the lower and upper boundaries for the Durbin-Watson statistic are approximately 1.7353 and 1.7697, respectively. What can be said about first-order autocorrelation given the Durbin-Watson value of 1.8911 calculated from the three factor model residuals?
2) The CAPM for Apple, which excludes the SMB and HML variables, has a beta (?) value of 1.3699, an R2 of 0.2119 and an F-ratio of 92.52. Has there been any appreciable gain in predictive power with the three factor model? Conduct a t-test on the null hypothesis that beta (?) truly equals 1.3699 given the above estimate of 1.2546 and its standard error of 0.1455. Also, comment on the CAPM intercept term of 1.1758 and its implications for investors given its statistical significance.
|
Variable - Parameter
|
Coefficients
|
Standard Errors
|
t-Statistics
|
|
Intercept - ?
|
1.1758
|
0.6505
|
1.8074
|
|
XRMKTt - ?
|
1.3699
|
0.1424
|
9.6186
|
3) For August 2011, the actual value of XRMKT is minus 2.65 (-2.65), SMB is plus 0.06 (+0.06) and HML is minus 2.17 (-2.17). The actual value for XRAAPL is 8.38 for August 2013. Given the three factor model above, what is the predicted value of XRAAPL for August 2013 in comparison to its actual value?