The Combination of Forecasts: An Application of a Time-Varying Simple Weighting Method to Inflation Forecasts in Turkey
International Research Journal of Applied Finance, Vol. 2, No. 3, pp. 270-301, March 2011
32 Pages Posted: 20 May 2011
Date Written: March 1, 2011
Abstract
We present a study on combining the forecasts from a time-series model and an econometric model in the context of the inflation rates of Turkey and propose a new weighting scheme, the time-varying simple weighting method. Our guiding principle for the deduction of this method is based on retaining the practicability and straightforwardness of simple averaging while avoiding the data-driven aspects of time-varying approaches. We further provide a topical and qualitative overview on the exhaustive literature of forecast combinations and apply our newly developed combination method to test for the prospective credibility of the inflation-targeting regime of the central bank of the Republic of Turkey.
Keywords: Forecast combination, Combination weights, Autoregressive Moving Average, Time Series, Forecast, Forecasting, Econometric modeling, Consumer Price Index, CPI, Inflation
JEL Classification: C32, C53, E37, E31
Suggested Citation: Suggested Citation
Do you have a job opening that you would like to promote on SSRN?
Recommended Papers
-
A Comparison of Linear and Nonlinear Univariate Models for Forecasting Macroeconomic Time Series
By James H. Stock and Mark W. Watson
-
By Marco Aiolfi, Carlos Capistrán, ...
-
Evaluation and Combination of Conditional Quantile Forecasts
-
Optimal Forecast Combinations Under General Loss Functions and Forecast Error Distributions
By Graham Elliott and Allan Timmermann
-
Unit Root Tests are Useful for Selecting Forecasting Models
By Francis X. Diebold and Lutz Kilian
-
Forecast Pooling for Short Time Series of Macroeconomic Variables