Inflation decomposition model : application to Macedonian inflation

The purpose of the paper is to introduce the framework for decomposing the forecast of headline inflation, obtained by macroeconomic model of NBRM for monetary policy analysis and medium term projections (MAKPAM), into its components: food, energy and core inflation. The model for inflation decomposition is a small structural model, set up in state space framework. Kalman filter procedure is applied to filter the future paths of CPI components, given projected headline inflation obtained by MAKPAM model and exogenous determinants, such as output gap, world commodity prices, and foreign effective inflation. The results of the model's forecasting performance suggest that this model can be a useful analytical tool in the process of inflation forecast, with relatively good fit of equations for food and domestic oil prices. This model serves as satellite model to MAKPAM and enriches the set of tools for forecasting and monetary policy analysis in NBRM. In this paper we highlight its most important equations, results and model performances.