Modeling the volatility of gross domestic product based on the volatility of money supply, inflation, interest rate, and exchange rate using the fractional cointegration model

Abstract

Economic growth is a quantitative index to determine the level of economic progress that can be measured by gross domestic product (GDP). Various literatures aim to solve problems regarding patterns of economic growth as well as about the determinants wherein the analysis volatility models are used. Some indicators of economic growth are money supply, inflation, interest rates, and exchange rates. Economic variables are recorded as time series data with different periods, and hence temporal aggregation is required to analyze. Economic time series data showing the existence of long memory and structural breaks, which leads to the difficulty on explaining the data only with a general model. Therefore, both long memory models and structural break are proposed to be taken into account in the model. In this analysis, the residual from a linear combination of economic variables follows a long memory process indicating a cointegration relationship between these variables. This paper models GDP volatility based on money supply, inflation, interest rate and exchange rate volatility in Indonesia, Philippines, Malaysia, and Singapore using the Fractional Cointegration model with long memory and structural break. The analysis shows that structural break is only found in the volatility of GDP of Indonesia, Malaysia, and Singapore while the nature of long memory is found in almost all economic variables' volatility. Furthermore, we found the cointegration model, stationary and persistent noise in all countries.