Abstract:
Gross domestic product (GDP) is the best way to measure a country’s economy. It includes everything produced by all the people and companies that are in the country. The objective of this paper is to empirically characterize the volatility models for GDP of Sri Lanka using seasonally adjusted at 2002 base year constant prices quarterly real GDP data for the period 2002:Q1 to 2015:Q4. The four types of ARCH family models (GARCH, TGARCH, EGARCH, PARCH) were used for the analysis data. Using various specifications for variance equation, study estimated ARIMA(1,2,2) Vs. GARCH(1,1), ARIMA(1,2,2) Vs. TGARCH(1,1), ARIMA(1,2,2) Vs. EGARCH(1,1) and ARIMA(1,2,2) Vs. PARCH(1,1) for real GDP. The comparison indicates that the ARIMA(1,2,2) Vs. EGARCH(1,1) model is the best model to modelling the volatility of real GDP. The results of the study present evidence that the symmetric response volatility of second differenced square root GDP to negative and positive shocks.
