Table 2.
Unit-root tests.
| Variablea | Augmented Dicker–Fuller |
Phillips–Perron |
||
|---|---|---|---|---|
| Lag length | t-Statistics | t-Statistics | ||
| Level | LGDPSA | 0 | −0.223 (<0.93) | −0.178 (<0.93) |
| LELECSA | 0 | −1.551 (<1.00) | −1.779 (<1.00) | |
| LPOP | 1 | −0.382 (<0.98) | −1.954 (<1.00) | |
| LTOURSA | 1 | −0.482 (<0.88) | −0.528 (<0.87) | |
| First-difference | ΔLGDPSA | 0 | −6.496 (<0.01)* | −6.500 (<0.01)* |
| ΔLELECSA | 0 | −6.671 (<0.01)* | −6.638 (<0.01)* | |
| ΔLPOP | 0 | −2.930 (0.05)** | −2.952 (<0.05)** | |
| ΔLTOURSA | 0 | −8.792 (<0.01)* | −10.671 (<0.01)* | |
| Second-difference | Δ2LGDPSA | 0 | −11.454 (<0.01)* | −14.592 (<0.01)* |
| Δ2LELECSA | 0 | −12.441 (<0.01)* | −36.927 (<0.01)* | |
| Δ2LPOP | 0 | −6.687 (<0.01)* | −6.721 (<0.01)* | |
| Δ2LTOURSA | 1 | −8.498 (<0.01)* | −31.021 (<0.01)* | |
Notes: For ADF tests, the optimal lag length was determined using Schwartz Information Criteria. The critical values of the ADF statistic at the 0.01, and 0.05 levels are −4.334, and −3.603 respectively (see MacKinnon [42]). * and ** denote the rejection of the null hypothesis at the 1 percent and 5 percent significance value, respectively and number in parentheses are the corresponding p-values.
a
Δ and Δ2 denote first-difference and second difference of variables.