Estimating inflation-at-risk (IaR) using extreme value theory (EVT)

Abstract

The Bangko Sentral ng Pilipinas (BSP) has the primary responsibility of maintaining stable prices conducive to a balanced and sustainable economic growth. The year 2008 posed a challenge to the BSP’s monetary policy making as inflation hit an official 17-year high of 12.5 percent in August after ten months of continuous acceleration. The alarming double-digit inflation rate was attributed to rising fuel and food prices, particularly the price of rice. A high inflation rate has impact on poverty since inflation affects the poor more than the rich. From a macroeconomic perspective, a high level of inflation is not conducive to economic growth. This paper proposes a method of estimating inflation-at-risk (IaR) similar to the value-at-risk (VaR) used to estimate risk in the financial markets. The IaR represents the maximum inflation over a target horizon for a given low pre-specified probability. It can serve as an early warning system that the BSP can use to identify whether the level of inflation is extreme enough to be considered an imminent threat to its inflation objective. Extreme value theory (EVT), which deals with the frequency and magnitude of very low-probability events, is used as the basis for building a model in estimating the IaR. The estimates of the IaR using the peaks-over-threshold (POT) model suggest that while the inflation rate experienced in 2008 cannot be considered as an extreme value, it was very near the estimated 90 percent IaR.

Classification-JEL: E31, C52, C01