Financial Innovation

Table 5 Goodness-of-fit and cross-validated statistics for linear and ANN models

From: Tax avoidance and earnings management: a neural network approach for the largest European economies

	GAAP_ETR		CASH_ETR		BTD
	Linear	ANN	Linear	ANN	Linear	ANN
m	0	2	0	1	0	1
RMSE	0.1362	0.1322	0.1626	0.1603	0.0211	0.0208
MAE	0.0915	0.0901	0.1194	0.1182	0.0109	0.0107
R-squared	0.1261	0.1765	0.0880	0.1136	0.3265	0.3482
No. parameters	31	95	31	63	31	63
Skewness	1.2352	1.0163	1.1368	1.0629	1.5251	0.2498
Kurtosis	7.3159	6.9381	5.3574	5.1879	86.2089	89.8842
SIC	−3.9600	−3.9641	−3.6003	−3.5956	−7.6923	−7.7020
AIC	−3.9811	−4.0285	−3.6254	−3.6466	−7.7099	−7.7378
CVRMSE	0.1370	0.1347	0.1637	0.1610	0.0224	0.0213
CVMAE	0.0921	0.0906	0.1201	0.1188	0.0110	0.0108

All variables are defined in the Appendix

Back to article page