Is the Phillips curve useful for forecasting infl ation in Russia?

Abstract

The paper analyzes the experience of using the Phillips curve to model inflation in Russia, taking into account the specific features of domestic labor market. Based on Russian data for the period from 2000 to 2022, a wide range of inflation forecasting models has been built: both based on the Phillips curve and alternative ones. The econometric tools used are autoregression models with a moving average in the residuals taking into account seasonality (SARIMA) and their generalizations; autoregression models of distributed lags (ADL) and their generalizations; as well as other estimation methods. During the simulation, we use data on inflation, inflation expectations, production dynamics, unemployment, wages, exchange rates, money supply and other variables. The models are compared drawing on the accuracy of single-period and multi-period out-of-sample forecasts. The modelling results allows us to conclude that onedimensional models work well during the periods of stable economic dynamics, but lose in their predictive power to the “triangular” Phillips curve in crisis years. Comparison of models for forecasting inflation shows that in a stable economic situation, one-dimensional models provide a more reliable forecast. However, in the context of structural transformation faced by the Russian economy in 2022, the “triangular” models of the Phillips curve demonstrate maximum quality of the forecast. Although the acceleration of inflation in 2022 obviously reduces the accuracy of any forecast equations, however, the “triangular” model based on the lags in inflation, unemployment and the index of industrial production demonstrates the best results. This conclusion remains stable to changes in the length of the time series used for forecasting, as well as to changes in forecasting horizon.