preview

Pt1420 Unit 4 Paper

Decent Essays

6. Technical Findings 6.1 Results of 10-year data Table 6.1.1 displays the matlab output of beta, standard error, t-statistic and p-value for the two independent variables during 10-year period. It is found that beta of X1 is 0.2750 which indicates there is a positive relationship between the utilities excess return and the healthcare excess return. This positive relationship is statistically significant as the p-value is close to 0 which is much less than the significance level of 5%. In addition, the standard error of X1 is 0.0300 which represents the average distance that the observed values fall from the regression line. This indicates that the model fits the data. In contrast, it is found that the material excess return is negatively …show more content…

Same as the results of 10-year period, the healthcare excess return is positively correlated with the utility excess return while negatively correlated with the material excess return. Compared to the 10-year results, it is found that beta of X1 decreases from 0.2750 to 0.2045 and beta of X2 decreases from -0.3165 to -0.3382. Also, beta of X0 drops which indicates without incorporating the event risk, more other variable is explained by the explanatory variables. As the p-value is less than 5% significance level, the relationships are both statistically significant. The standard errors of X1 and X2 are both small enough to indicate that the observations are close to the fitted …show more content…

And the outputs of both dataset are consisted with the results applying the robust function. Betas stay the same and only the standard errors in both cases decline slightly. Similarly, the graphs in both cases remain the same. Based on the non-robust test, we then can confirm that the variables are independent and uncorrelated, which satisfies the easing assumption to state the model is consistent. 7. Criticism Referring to Figure 6.2.3 and 6.3.3, it was proven that our model has problems that the sample data used does not represent the whole population. Therefore, this is one of the flaws in our research. A more constructive suggestion to eliminate this problem would be to extend the research with a larger sample size with longer time horizon. And if the sample size is large enough, the time series issue can be neglected. Another issue might arise by the determination of explanatory variables. As we follow the facesheet from Morningstar (2011) to choose our explanatory variables as a symbol of the defensive sectors and cyclical sectors, it is possible that the category of sectors is incorrect. Without the support of academic journals, the facesheet might be purely based on analysts ‘opinions instead of facts. By estimating wrong explanatory variables, the findings will become

Get Access