Answers are grounded in this paper and cite their sources.
Forecasting of time series is important subject in macroeconomics. We use two time series methods. One of the most simple and basic method for forecasting time series is decomposition. Decomposing the time series means breaking the time series into four components, i.e., trend, cycle, seasonal and irregular. The second method is based on ARIMA model. In this paper we forecast the macroeconomic variables CPI, and LSM for period July 2013 to September 2013, based on decomposition of actual series of these variables and ARIMA model for monthly series from July 2008 to June 2013. We compare the out-of-sample forecast of two methods based on the mean absolute deviation (MAD) & sum of square of errors (SSE) and decide on which method provides the best forecasting accuracy which policy makers can rely on in forecasting inflation (CPI) and Economic growth (LSM).
No takes yet. Share an insight, caveat, or question.
Kishwer Sultana (2013) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: