Table 6 PLSp redict and CVPAT results...

Table 6

PLSpredict and CVPAT results

Construct	PLSpredict					CVPAT
Construct	Item	Q²predict	PLS-SEM_RMSE	LM_RMSE	Decision	IA average loss difference (p-value)	LM average loss difference (p-value)	Decision
ORR	ORR1	0.175	0.845	0.906	High	−0.137 (0.000)	−0.074 (0.006)	Strong predictive validity
	ORR2	0.141	1.029	1.072
	ORR3	0.203	0.696	0.734
	ORR4	0.207	0.699	0.745
	ORR5	0.194	0.754	0.806
	ORR6	0.197	0.705	0.752
	ORR7	0.186	0.731	0.763
SUC	SUC1	0.203	0.973	0.983	High	−0.212 (0.000)	−0.030 (0.196)	Predictive validity
	SUC2	0.253	0.897	0.912
	SUC3	0.186	0.804	0.821
	SUC4	0.358	0.881	0.906
	SUC5	0.316	0.965	0.985
	SUC6	0.245	0.920	0.930
Overall						−0.212 (0.000)	−0.053 (0.009)	Strong predictive validity

Construct	PLSpredict					CVPAT
Construct	Item	Q²predict	PLS-SEM_RMSE	LM_RMSE	Decision	IA average loss difference (p-value)	LM average loss difference (p-value)	Decision
ORR	ORR1	0.175	0.845	0.906	High	−0.137 (0.000)	−0.074 (0.006)	Strong predictive validity
	ORR2	0.141	1.029	1.072
	ORR3	0.203	0.696	0.734
	ORR4	0.207	0.699	0.745
	ORR5	0.194	0.754	0.806
	ORR6	0.197	0.705	0.752
	ORR7	0.186	0.731	0.763
SUC	SUC1	0.203	0.973	0.983	High	−0.212 (0.000)	−0.030 (0.196)	Predictive validity
	SUC2	0.253	0.897	0.912
	SUC3	0.186	0.804	0.821
	SUC4	0.358	0.881	0.906
	SUC5	0.316	0.965	0.985
	SUC6	0.245	0.920	0.930
Overall						−0.212 (0.000)	−0.053 (0.009)	Strong predictive validity

Note(s): Q²predict = Predictive relevance; PLS-SEM = Partial least squares structural equation modelling; LM = Linear model; MAE = Mean absolute error. CVPAT = cross-validated predictive ability test; IA = indicator average. ORR = Organisational resilience; SUC = Sustainable competitiveness

Source(s): Authors’ own work

[ViewLarge]

Sharing Unavailable