AN APPLICATION OF THE PANEL VECTOR AUTOREGRESSIVE MODEL TO ANALYZE INFLATION AND GRDP GROWTH RATES

Abstract

The Panel Vector Autoregressive (PVAR) model is an extension of the traditional Vector Autoregressive (VAR) framework that is specifically designed for panel data, allowing the integration of time-series and cross-sectional information across multiple regions. One of the main advantages of the PVAR approach is its ability to treat all variables as endogenous and to capture dynamic interdependencies simultaneously. This study aims to examine the dynamic relationship between inflation and regional economic growth, as measured by Gross Regional Domestic Product (GRDP) growth, across provinces in Indonesia using a PVAR model. The empirical analysis begins with panel unit root testing employing the Im–Pesaran–Shin (IPS) test to ensure stationarity of the variables, followed by optimal lag length determination based on the Moment and Model Selection Criteria (MMSC). Model estimation is conducted using the Generalized Method of Moments (GMM) to address endogeneity and unobserved heterogeneity. The validity of the instruments is evaluated through the Sargan–Hansen test, while causal linkages between variables are investigated using the Granger causality test. The results reveal evidence of a bidirectional relationship between inflation and economic growth in several provinces, indicating dynamic feedback effects. Stability tests confirm that the estimated PVAR model is stable. Furthermore, Impulse Response Function (IRF) and Forecast Error Variance Decomposition (FEVD) analyses illustrate how shocks to inflation and economic growth propagate over time. These findings provide valuable insights for designing more effective and regionally targeted economic policies in Indonesia.