<abstract xmlns="http://www.w3.org/1999/xhtml"><p>We evaluate the forecasting performance of four competing models for short-term macroeconomic forecasting: the traditional VAR, small scale Bayesian VAR, Factor Augmented VAR and Bayesian Factor Augmented VAR models. Using Armenian quarterly actual macroeconomic time series from 1996Q1 – 2014Q4, we estimate parameters of four competing models. Based on the out-of-sample recursive forecast evaluations and using root mean squared error (RMSE) criterion we conclude that small scale Bayesian VAR and Bayesian Factor Augmented VAR models are more suitable for short-term forecasting than traditional unrestricted VAR model.</p></abstract>

We evaluate the forecasting performance of four competing models for short-term macroeconomic forecasting: the traditional VAR, small scale Bayesian VAR, Factor Augmented VAR and Bayesian Factor Augmented VAR models. Using Armenian quarterly actual macroeconomic time series from 1996Q1 – 2014Q4, we estimate parameters of four competing models. Based on the out-of-sample recursive forecast evaluations and using root mean squared error (RMSE) criterion we conclude that small scale Bayesian VAR and Bayesian Factor Augmented VAR models are more suitable for short-term forecasting than traditional unrestricted VAR model.

A Comparison of Different Short-Term Macroeconomic Forecasting Models: Evidence from Armenia

Central Bank of Armenia, Economic Research Department

Journal of Central Banking Theory and Practice

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

We evaluate the forecasting performance of four competing models for short-term macroeconomic forecasting: the traditional VAR, small scale Bayesian VAR,...

A Comparison of Different Short-Term Macroeconomic Forecasting Models: Evidence from Armenia

Publicado en línea: 20 may 2016

Páginas: 81 - 99

Recibido: 02 sept 2015

Aceptado: 19 oct 2015

DOI: https://doi.org/10.1515/jcbtp-2016-0012

Palabras clave
vector autoregression, Bayesian estimation, principal components, recursive regression, forecast evaluation, macroeconomic indicators, Armenia

© 2016 Central Bank of Montenegro

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

A Comparison of Different Short-Term Macroeconomic Forecasting Models: Evidence from Armenia

Publicado en línea: 20 may 2016

Páginas: 81 - 99

Recibido: 02 sept 2015

Aceptado: 19 oct 2015

DOI: https://doi.org/10.1515/jcbtp-2016-0012

Palabras clavevector autoregression, Bayesian estimation, principal components, recursive regression, forecast evaluation, macroeconomic indicators, Armenia

© 2016 Central Bank of Montenegro

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Palabras clave
vector autoregression, Bayesian estimation, principal components, recursive regression, forecast evaluation, macroeconomic indicators, Armenia