英语论文网

rom the regression are stationary. If significant ADF test is obtained from the test, then we can conclude that the variables are cointegrated.

ADF检验残差的平稳性——ADF Test for stationarity of residuals

In absolute terms, the t-statistic is greater than the critical value in both equations. Therefore the variables cointegrate despite the fact that they are individually non-stationary. Hence it can be concluded that there is a long run relationship between exports and its explanatory variables and between imports and its explanatory variables. Consequently we can proceed to estimate the long run equation.

4.4 多重共线性检验——4.4 Test for Multicollinearity

Multicollinearity exist when there is a near perfect linear relationship among the predictors in a model. As the degree of multicollinearity increases, the regression model estimates of the coefficients become unstable and the standard errors for the coefficients can get wildly inflated. The variance inflation factor(VIF) can be used to detect presence of multicollinearity. As a rule of thumb, a variable whose VIF values are greater than 10 imply that the variable could be considered as a linear combination of other independent variables.

4.5 模型规范测试——4.5 Model Specification Test

A model specification error can occur when one or more relevant variables are omitted from the model or one or more irrelevant variables are included in the model. The linktest can be used to detect specification errors.

The linktest creates 2 new variables, hat which is the variable of prediction and hatsq, the variables of squared prediction. The model is then refit using these two variables as predictors. While the hat is expected to be statistically significant, hatsq is expected to be insignificant since if our model is specified correctly, the squared predictions should not have much explanatory power. The linktest shows that test statistics of hatsq is not significant. Therefore the linktest has failed to reject the assumption that the model is specified correctly.

4.6 评估的结果导出功能——4.6 Estimation result of Export Function

4.6.1 长期方程——4.6.1 The Long run equation

Table 5 depicts the results for the short run equation. The results indicate that except for LCU and LV, all the variables are statistically significant. Therefore volatility is not statistically significant in explaining export volume, that is, it does not have any effect on the volume of exports to the USA in the long run. The result support the results obtained by Hooper and Kohlhagen (1978), Bahmani et Tavlas.(1988), Bailey et al.(1986), Cushman(1983) and recently Klassen(2004) who found no evidence of a significant relationship between volatility and international trade in their studies. This can be explained by the fact that in Mauritius operates under a managed float exchange rate regime and hence volatility is quite small compared to other countries which operate a freely floating exchange rate system.

The coefficient of LCU also is insignificant and hence capital utilisation does not have any effect on volume exported to the USA. This is in line with the results obtained by Medh