Improving Forecasts of the EGARCH Model Using Artificial Neural Network and Fuzzy Inference System

Table 8

Statistical properties of residual data.

Statistical properties of residual data
Min.	−0.453063
Max.	0.600486
Mean	0.000000
Median	−0.000187
Variance	0.014241
Skewness	0.169104
Kurtosis	4.270338
Arch test	value = 8.0384e − 09
Jarque–Bera test (for alpha = 0.05)	value = 4.4409e − 16

Mean   smedian usually flags left skewness. Negative skewness means left-skewed data. Kurtosis >3 means larger peakedness than Gaussian. Arch test result with very small value implies existence of strong heteroskedasticity. Jarque–Bera test result with very small value implies that the residual series strongly follows Student’s t-distribution.