Forecasting Inflation - An Empirical Study on Predictive Power of Various Time-Series Models
1 online resource (60 pages) : PDF
University of North Carolina at Charlotte
In this thesis, I investigate the background and causes of major inflation in recent history and empirically study forecasting of future quarterly inflation rates for three typical countries and regions: the United States, the United Kingdom, and the Eurozone. In particular, I empirically investigate the predictive power of four commonly used econometric models: the AR model, the ADL model, the ARIMA model, and the VAR model. I compare each model’s forecasting accuracy by calculating the corresponding RMSFE (Root Mean Squared Forecast Error) of pseudo-out-of-sample forecasting for each country or region. The model that exhibits the smallest RMSFE is my preferred model. The results suggest that, for each country or region in my dataset, the ARIMA model significantly outperforms the other three models. By determining ARIMA as the most preferable model, I use the ARIMA model to forecast the future (two-year ahead) quarterly inflation rate.
ADVANCE BUSINESS FORECASTINGECONOMETRIC
Azhal, IqbalMatthew, Metzgar
Thesis (M.S.)--University of North Carolina at Charlotte, 2015.
This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s). For additional information, see http://rightsstatements.org/page/InC/1.0/.
Copyright is held by the author unless otherwise indicated.