AN EARLY WARNING SYSTEM FOR INFLATION IN THE PHILIPPINES USING MARKOV-SWITCHING AND LOGISTIC REGRESSION MODELS

Abstract

With the adoption of the Bangko Sentral ng Pilipinas (BSP) of the Inflation Targeting (IT) framework in 2002, average inflation went down in the past decade from historical average. However, the BSP’s inflation targets were breached several times since 2002. Against this backdrop, this paper develops an early warning system (EWS) model for predicting the occurrence of high inflation in the Philippines. Episodes of high and low inflation were identified using Markov-switching models. Using the outcomes of regime classification, logistic regression models are then estimated with the objective of quantifying the possibility of the occurrence of high inflation episodes. Empirical results show that the proposed EWS model has some potential as a complementary tool in the BSP’s monetary policy formulation based on the in-sample and out-of sample forecasting performance.