Inflation forecasts using Bayesian Techniques
DOI:
https://doi.org/10.15359/eys.20-48.3Keywords:
productive development, entrepreneurs, methodology of extensiveness, social vulnerabilityAbstract
The effective monetary policy using the inflation targeting scheme proposed by the Central Bank of Costa Rica is mostly based on the correct and timely inflation forecast in the short and medium term, in order to better design monetary policy actions. The purpose of this study is to develop a complementary tool to forecast inflation using a Bayesian approach. To that end, we propose using the Bayesian Model Averaging and Weighted-Average Least Squares methodologies. Such projection models allow expanding and complementing the analysis currently conducted by the Central Bank of Costa Rica using the Quarterly Macroeconomic Projection Model (MQPM). As a result, we show that for monthly data and forecasting 1 to 12 months in advance, it is possible to have projections using the Bayesian process with greater predictive performance than with the autoregressive model.
References
Álvarez, C., & Torres, C. (2011). Modelos de Inflación de Corto Plazo para los Sectores Transable y No Transable de la Economía Costarricense (Documento de Investigación No. 04-2011). Recuperado del sitio de internet del Banco Central de Costa Rica, Departamento de Investigación Económica: http://www.bccr.fi.cr/investigacioneseconomicas/politicamonetariaeinflacion/Modelos_inflacion_cp_sectores_transable_y_no_transable_economia_costarricense.pdf
Brissimis, S., & Magginas, N. (2008). Inflation Forecast and the New Keynesian Phillips Curve, International Journal of Central Banking. Recuperado de http://www.ijcb.org/journal/ijcb08q2a1.htm
Danilov, D., & Magnus, J. (2004). Forecast Accuracy After Pretesting with an Application to the Stock Market, Journal of Forecasting, 23(4), 251-274. http://dx.doi.org/10.1002/for.916
De Luca, G., & Magnus, J (2011). Bayesian Model Averaging and Weighted Average Least Squares: Equivariance, Stability, and Numerical Issues (Center Working Paper No. 2011-082). http://dx.doi.org/10.2139/ssrn.1894610
Diebold, F., & Mariano, R. (1995). Comparing predictive accuracy, Journal of Business and Economic Statistics 13(3), 253-263. http://dx.doi.org/10.1080/07350015.1995.10524599
Esquivel, M., Rodríguez, A., & Vásquez, J. (2011). Medias truncadas del IPC como indicadores de inflación subyacente en Costa Rica (Documento de investigación No. 01-2011). Recuperado del sitio de internet del Banco Central de Costa Rica, Departamento de Investigación Económica: http://www.bccr.fi.cr/investigacioneseconomicas/politicamonetariaeinflacion/Medias%20truncadas_del_IPC_como_indicadores_de_inflacion_subyacente_en_CR.pdf
Fernández, C., Ley, E., & Steel, M. (2001). Benchmarks priors for Bayesian model averaging, Journal of Econometrics 100(2), 381-427. http://dx.doi.org/10.1016/S0304-4076(00)00076-2
Goel, P. (1986). On Assessing Prior Distributions and Bayesian Regression Analysis with g-Prior Distributions. En Zellner, A (Ed), Bayesian Inference and Decision Techniques: Essays in Honour of Bruno de Finetti (Studies in Bayesian Econometrics and Statistics, Vol.6). Recuperado de http://www.amazon.com/Bayesian-Inference-Decision-Techniques-Econometrics/dp/0444877126
Hoffmaister, A., Saborío, G., & Vindas, K. (2000). Proyecciones de Inflación: Innovaciones en los Precios Agrícolas y Regulados, y Ajustes (Nota de Investigación No. 7-00). Recuperado del sitio del Banco Central de Costa Rica, Departamento de Investigación Económica. Recuperado de http://www.bccr.fi.cr/investigacioneseconomicas/politicamonetariaeinflacion/Proyecciones_Inflacion,_Innovaciones_Precios_Agricolas_Regulados_Ajustes.pdf
Magnus, J., Powell, O., & Prüfer, P. (2010). A comparison of two model averaging techniques with an application to growth empirics, Journal of econometrics 154(2), 139-153. http://dx.doi.org/10.1016/j.jeconom.2009.07.004
Magnus, J., & Durbin, J. (1999). Estimation of regression coefficients of interest when other regression coefficients are of no interest, Econometrica Journal of Econometric Society 67(3), 639-643. http://dx.doi.org/10.1111/1468-0262.00040
Muñoz, E. (2008). Validación del Modelo Univariable de Inflación empleado en la Combinación de Pronósticos (Informe técnico DIE-08-2008). Recuperado del sitio del Banco Central de Costa Rica, Departamento de División Económica: http://www.bccr.fi.cr/investigacioneseconomicas/politicamonetariaeinflacion/Validacion_Modelo_Univariable_Inflacion_empleado_Combinacion_Pronosticos.pdf
Rodríguez, A. (2009). Evaluación del modelo lineal pass-through para la proyección de inflación dentro del régimen de banda cambiaria (Documento de Investigación 07-2009). Recuperado del sitio de internet del Banco Central de Costa Rica, Departamento de Investigación Económica: http://www.bccr.fi.cr/investigacioneseconomicas/politicamonetariaeinflacion/Evaluacion_modelo_lineal_pass_through_proyeccion_inflacion_regimen_banda_cambiaria.pdf
Steel, M. (2014). Bayesian model averaging and forecasting. Recuperado de http://www2.warwick.ac.uk/fac/sci/statistics/staff/academic-research/steel/steel_homepage/publ/bma_forecast.pdf
Vindas, A. (2011). Validación del modelo ARMA para la proyección de la inflación en Costa Rica (Serie Documentos de Trabajo No. 03-2011). Recuperado del sitio del Banco Central de Costa Rica, Departamento de Investigación Económica: http://www.bccr.fi.cr/investigacioneseconomicas/politicamonetariaeinflacion/Validacion_del_modelo_arma_para_la_inflacion.pdf
Downloads
Published
How to Cite
Issue
Section
License
This publication is subject to the Creative Commons License; therefore, its attributions and restrictions must be respected.
Authors publishing in this Journal accept the following conditions:
- Authors retain copyright ownership and give the Journal first publication right of the paper, which is registered with the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. This license allows third parties to use the published work provided it is sourced as firstly published in this Journal.
- Authors may enter into other independent and additional contractual agreements for the non-exclusive distribution of the article published in this Journal (e.g., to be included in an institutional repository or published in a book) provided it is clearly stated that the work was published in this Journal for the first time.
- Authors are allowed and recommended to publish their work on the Internet (for example, on institutional or personal pages) before and during the review and publication process, as it can lead to productive exchanges and a greater and faster dissemination of work published.
The Economía & Sociedad Journal, published by Universidad Nacional, is licensed under a Creative Commons Reconocimiento-NoComercial-CompartirIgual 4.0 Internacional License. Based on http://www.revistas.una.ac.cr/index.php/economia.
