The effect of individual factors on user behaviour and the moderating role of trust: an empirical investigation of consumers’ acceptance of electronic banking in the Kurdistan Region of Iraq

Financial Innovation

Table 7 PLSpredict assessment of manifest variables (original model)

Item	PLS-SEM		LM	PLS-SEM-LM*
Item	MAE	Q²_predict	MAE	MAE
PE4	0.505	0.452	0	0.505*
SI13	0.718	0.112	0	0.718*
PE1	0.377	0.568	0	0.377*
FC20	0.579	0.441	0	0.579*
EE9	0.253	0.828	0	0.253*
EE12	0.307	0.709	0	0.307*
EE8	0.290	0.737	0	0.29*
PE2	0.383	0.581	0	0.383*
SI18	0.553	0.114	0	0.553*
EE10	0.320	0.695	0	0.32*
EE11	0.333	0.679	0	0.333*
SI17	0.797	0.086	0	0.797*
EE7	0.304	0.720	0	0.304*
FC19	0.601	0.408	0	0.601*
PE3	0.746	0.189	0	0.746*
PE5	0.767	0.186	0	0.767*
PE6	0.503	0.391	0	0.503*
FC22	0.764	0.206	0	0.764*
UB67	0.527	0.369	0.476	0.051*
UB64	0.604	0.441	0.535	0.069*
UB65	0.529	0.401	0.499	0.03*
UB66	0.561	0.441	0.507	0.054*

*PLS-SEM < LM for none of the indicators. If the PLS-SEM analysis (compared to the LM) yields lower prediction errors in terms of the MAE (or the RMSE) for none of the indicators, this indicates that the model lacks predictive power
**PLS-SEM < LM for a minority of the indicators. If the minority of the dependent construct’s indicators produces lower PLS-SEM prediction errors compared to the naïve LM benchmark, this indicates that the model has a low predictive power
***PLS-SEM < LM for a majority of the indicators. If the majority (or the same number) of indicators in the PLS-SEM analysis yields smaller prediction errors compared to the LM, this indicates a medium predictive power
****PLS-SEM < LM for all indicators. If all indicators in the PLS-SEM analysis have lower MAE (or RMSE) values compared to the na.ve LM benchmark, the model has high predictive power