China Policy Journal Volume 1, Number 1, Fall 2018 | Page 48

Assessing the Implementation of Local Emission Trading Schemes in China
Break2015 0.018 0.025 0.026 −0.013 −0.017* −0.017*
(0.019) (0.018) (0.018) (0.009) (0.009) (0.009)
Break2016 0.026 0.023 0.020 0.005 0.007 0.007
(0.019) (0.019) (0.019) (0.012) (0.012) (0.012)
Constant −0.003 −0.002 −0.001 −0.008 −0.007 −0.007
(0.013) (0.013) (0.015) (0.005) (0.005) (0.006)
Obs. 181 181 179 167 167 167
R-squ. 0.117 0.121 0.132 0.034 0.050 0.055
F-stat. 2.150 1.900 1.660 0.510 0.640 0.870
Prob>F 0.028 0.043 0.074 0.863 0.796 0.588
Durbin's
alternative test
2.190 1.954 1.676 0.001 0.285 0.523
BG LM test 2.302 2.081 1.811 0.001 0.309 0.572
Procedure OLS, robust OLS, robust OLS, robust OLS, robust OLS, robust OLS, robust
Joint F-stat for
D.lnBrent t
0.240 0.240 0.330 0.540 0.580 0.630
Joint F-stat for
D.lnCoal t
2.040 1.850 1.940 0.470 0.440 0.510
Joint F-stat for
D.lnLNG t
0.650 0.400
Joint F-stat for
D.lnStock t
0.370 0.300 1.140 1.350
Note: The dependent variable is the price returns (lnReturn t
) of CEA in the ETS. Durbin’s alternative
test and Breusch–Godfrey (BG) LM test are the tests for autocorrelation. “Joint F-stat” refers
to the F statistic of the joint significance test on the lags of log differences of energy variables and
the stock index variable. ***, ** and * denote significance at 1%, 5% and 10% levels. Standard errors
are in parentheses.
ferences of energy prices and the stock
index as well as the structural break
dummies. The regressions are all estimated
using the robust estimator rather
than Newey-West estimator as there is
no significant serial correlation problem.
The last four rows of Table 8 show
the results of the joint F-tests, which
test the joint significance of coefficients
on all lag values of a variable.
We can see that the one week
lagged coal price return (D.lnCoal t
) had
a significantly negative effect on Guangdong
CEA price returns. It means that
the increase of coal price led to the
decrease of Guangdong CEA price in
short term, which is consistent with the
theory that when coal price is high, the
industrial enterprises substitute coal
with less carbon-intensive fuels, reducing
CEA demand. But, the short-term
effect became insignificant after two
weeks. The joint F-test indicates that the
changes in coal price do not significant-
45