| (1) | (2) | (3) | (4) | (5) | (6) | (7) | (8) |
---|
Constant | − 0.21 (0.58) | − 0.21 (0.68) | 0.22 (0.61) | − 0.04 (0.51) | − 0.11 (0.37) | − 0.09 (0.5) | 0.04 (0.46) | 0.01 (0.44) |
Δ(TD-MD)/GDP | 0.44 (0.47) | | 0.56 (0.49) | | 0.4 (0.44) | | 0.34 (0.45) | |
ΔMD/GDP | 0.68 (0.54) | 1.04 (0.9) | | | 0.76 (0.55) | 0.91 (0.76) | | |
ΔSSTD (t-1) | 0.45** (0.17) | | | 0.53** (0.19) | 0.2 (0.18) | | | 0.29 (0.21) |
Adjusted R2 | 0.27 | 0.88 | 0.01 | 0.26 | 0.08 | 0.06 | − 0.01 | 0.06 |
Box-Ljung (3) | 0.33 | 0 | 0.06 | 0.39 | 0.84 | 0.09 | 0.3 | 0.94 |
Observations | 27 | 28 | 28 | 27 | 45 | 46 | 46 | 45 |
- This table reports regressions with ΔSSTD as dependent variable. The dataset contains yearly observations. Column 1 displays the baseline regression, whereas columns 2–8 display specific robustness checks. Column 1 to 4 is based on yearly observations from 1980 to 2008 and column 5 to 8 from 1970 to 2016. ***, **, and * denote statistical significance (two-tailed) at the 1%, 5%, and 10% significance level respectively. Standard errors are reported in parentheses. For columns 4, 5, and 8, heteroscedasticity-consistent (Huber-White) standard errors are used. Columns 2 and 6 displays Newey-West standard errors due to serial correlation. Due to the small number of observations, for columns 1, 3, and 7 we use normal standard errors that are larger than the Huber-White or Newey-West standard errors. To test for serial correlation of the error term, we perform the Box-Ljung test and report its p-value. We use a lag of 3 (considering the small sample size)