Inflation threshold, fiscal conditions and growth stability in Nigeria’s post-shock macroeconomic environment

This study examines the nonlinear relationship between inflation and economic growth in Nigeria within a post-shock macroeconomic environment using annual data from 1990 to 2025. The empirical analysis combines Ordinary Least Squares estimation with Newey–West heteroskedasticity and autocorrelation-consistent standard errors, time-series threshold regression, smooth transition regression, inflation–fiscal interaction modelling, structural-break and parameter-stability diagnostics, quantile regression, and complementary machine-learning techniques for exploratory nonlinear assessment. The results indicate that inflation is negatively and statistically significantly associated with real GDP growth and that the magnitude of this relationship varies across inflation regimes. The threshold model identifies an estimated inflation threshold of 12.22%, with negative inflation coefficients observed both below and above the threshold. A sensitivity analysis excluding the three boundary observations affected by completion of the trade-openness series retains the 12.22% threshold and produces closely comparable regime coefficients, indicating that the principal threshold result is not materially driven by the data-completion procedure. The smooth transition model identifies a comparable transition location of approximately 11.50%; however, its transition parameters are not statistically significant, indicating that the evidence for gradual regime adjustment is weaker than that obtained from the threshold model. Exchange-rate depreciation and international Brent crude oil-price shocks are negatively associated with growth in the baseline specification, although their independent statistical significance weakens after nonlinear inflation dynamics are incorporated. The positive and statistically significant interaction between inflation and fiscal balance indicates that improved fiscal positions may attenuate, but not eliminate, the adverse association between inflation and growth. Trade openness is positively associated with growth, whereas broad money growth exhibits a negative baseline relationship, although these effects vary across specifications. Structural-break tests identify breaks in 2016, 2020, and 2023, corresponding to Nigeria’s recession, the COVID-19-related economic disruption, and exchange-rate liberalisation reforms. Quantile regression provides complementary distribution-sensitive evidence, whereas chronologically ordered hold-out validation indicates limited temporal generalisation of the Random Forest and XGBoost models; their feature-importance and SHAP outputs are therefore interpreted as exploratory nonlinear evidence rather than independent predictive or causal confirmation. Overall, the findings show that Nigeria’s inflation–growth relationship is negative, regime-sensitive, and conditioned by fiscal and external macroeconomic circumstances, underscoring the importance of coordinated monetary, fiscal, and exchange-rate policies.