Table 8

Diagnostic tests

TestNull hypothesisWald statistic (F)p-value
W–LGDPPCNo long-run asymmetry0.0520.821
W–LCPINo long-run asymmetry32.5200.000
W–INTERNo long-run asymmetry41.8900.000
W–ΔLGDPPCNo short-run asymmetry5.7400.020
W–ΔLCPINo short-run asymmetry5.7800.019
W–ΔINTERNo short-run asymmetry10.5100.002
TestNull hypothesisStatisticp-value
Jarque-BeraNormality of residuals0.0790.961
LM (Breusch–Godfrey)No serial correlation in residuals0.1050.363
Breusch-Pagan-GodfreyHomoscedasticity of residuals28.4360.056
Ramsey resetThe model is correctly specified1.9990.163
Durbin–WatsonTest for autocorrelation2.014

Note(s): Centered VIFs (NARDL regressors) range 1.75–4.21 (max 4.21), no material multicollinearity

Source(s): Authors' calculations; created by authors

or Create an Account

Close subscription notice
Close access options