The Brown Bag Lunch is a weekly series where professors and doctoral students present their ongoing research. This week's speaker is Meri Papavangjeli, BCC Fellow at the Bank of Albania, giving a talk entitled
Forecasting the Albanian short-term inflation through a Bayesian VAR model
Abstract | In the context of the Bank of Albania's primary objective of achieving and maintaining price stability, generating accurate and reliable forecasts for the future rate of inflation is a necessity for the successful realization of this objective. This project aims to enrich the Bank’s portfolio of short-term inflation forecasting tools through the construction of a Bayesian VAR model, which unlike standard autoregressive vector models, addresses the over-parameterization problem, allowing the inclusion of more endogenous variables, and enabling in this way a more comprehensive explanation of inflation. Several univariate models are estimated to forecast short-term inflation, such as: unconditional mean, random walk, autoregressive and seasonal autoregressive integrated moving average models, and the best performing among them is used as a benchmark to evaluate the forecast performance of the BVAR model. The results show that the BVAR approach, which incorporates more economic information, outperforms the benchmark univariate models in different time horizons of the forecast sample.