Appendix
Figure 5 Graph of Residuals (STEPLS)
Regarding the histogram in the table one is unable to identify a trend in the residuals. Thus, there is so far no suspicion of heteroscedasticity. This is confirmed by executing the White and Breusch-Pagan- Godfrey test (see Table 13 and Table 14 respectively).
Table 13 White-test
F-statistic 1.014486 Prob. F(7,83) 0.4272
Obs*R-squared 7.172225 Prob. Chi-Square(7) 0.4112 Scaled explained SS 9.119026 Prob. Chi-Square(7) 0.2442
Table 14 Breusch Pagan Godfrey Heterscesticity test (STEPLS)
F-statistic 2.206877 Prob. F(3,87) 0.0930
Obs*R-squared 6.435307 Prob. Chi-Square(3) 0.0922 Scaled explained SS 8.182081 Prob. Chi-Square(3) 0.0424
Table 15 Breusch – Godfrey Autocorrelation test (STEPLS)
With respect to Table 15 and the results of the Breusch-Godfrey test we do not find evidence of autocorrelation.
F-statistic 1.481607 Prob. F(2,85) 0.2331
Obs*R-squared 3.065514 Prob. Chi-Square(2) 0.2159
-.2 -.1 .0 .1 .2
0.6 0.7 0.8 0.9 1.0 1.1
1 6 11 16 24 31 37 43 48 53 59 64 73 79 84 89 95 100 106 113 118 124 128
Residual Actual Fitted
-.2 -.1 .0 .1 .2
0.6 0.7 0.8 0.9 1.0 1.1
1 6 11 16 24 31 37 43 48 53 59 64 73 79 84 89 95 100 106 113 118 124 128
Residual Actual Fitted