Unobserved Component Model for Forecasting Polish Inflation
Journal Title: Dynamic Econometric Models - Year 2010, Vol 10, Issue 1
Abstract
This paper aims to use the local level models with GARCH and SV errors to predict Polish inflation. The series to be forecast, measured monthly, is consumer price index (CPI) in Poland during 1992-2008. We selected three forecasting models i.e. LL-GARCH(1,1) with Normal or Student errors and LL-SV. A simple AR(2)-SV model is used as a benchmark to assess the accuracy of prediction. The presented results indicate, that there is no clear advantage of LL models in forecasting Polish inflation over standard AR(2)-SV model, although all the models give satisfactory results.
Authors and Affiliations
Jacek Kwiatkowski
Distribution Choice for the Asymmetric ACD Models
In the paper, I generalize the Asymmetric Autoregressive Conditional Duration (AACD) model proposed by Bauwens and Giot (2003) with respect to the generalized gamma and the Burr distribution for an error term. I derive...
Forecasting EUR/PLN Exchange Rate: the Role of Purchasing Power Parity Hypothesis in ESTVEC Models
The purpose of this paper is to verify strong-form purchasing power parity (PPP) of EUR/PLN within a class of smooth transition vector error correction models (ESTVECM). Empirical importance of exponential smooth transit...
Determinants of Corporate Performance: Modelling Approach
This study is to investigate the influence of the selected factors of the capital structure on the corporate performance. An empirical analysis covers a sample of 90 non-financial companies traded on the Warsaw Stock Exc...
Discrete Spectral Analysis. The Case of Industrial Production in Selected European Countries
The aim of this paper is to show the usefulness the discrete spectral analysis in identification cyclical fluctuations. The subsampling procedure was applied to construct the asymptotically consistent test for Fourier co...
Combined Forecasts Using the Akaike Weights
The focus in the paper is on the information criteria approach and especially the Akaike information criterion which is used to obtain the Akaike weights. This approach enables to receive not one best model, but several...