A Hybrid LSTM-Based Ensemble Learning Approach for China Coastal Bulk Coal Freight Index Prediction

Table 1

Descriptive statistics of daily CBCFI and rate of change of CBCFI.

Statistic	Daily CBCFI	Rate of change for CBCFI
Mean	722.6500	−0.0002
Median	675.4800	−0.0012
Standard deviation	223.8494	0.0228
Maximum	1,706.2000	0.1186
Min	370.9900	−0.1337
Kurtosis	1.7801	5.6084
Skewness	1.2186	0.2550
J-B	658.9484	626.4104
value	0.000	0.000
ADF [lags]	−4.5298 [12]	−11.3960 [12]
value	0.0130	0.0164
Q [lags]	26.571 [6]	15.95 [6]
value	0.000	0.000
Observation	2129	2128

Note. J-B represents the Jarque-Bera (J-B) test in which a goodness-of-fit test is performed for examining whether the time series follows a normal distribution [42]. ADF represents the augmented Dickey-Fuller (ADF) test with a null hypothesis of the existence of autocorrelation in the sample series [43]. represents the Ljung-Box statistics to the squared residuals (also known as Q-Statistics of Square Residuals) in which a nonlinearity test [44] under the null hypothesis of linearity and residuals of a properly specified linear model should be independent [45].