A Comparison Between Direct and Indirect Seasonal Adjustment of the Chilean GDP 1986–2009 with X-12-ARIMA
- 12 Downloads
It is well known among practitioners that the seasonal adjustment applied to economic time series involves several decisions to be made by the econometrician. As such, it would always be desirable to have an informed opinion on the risks taken by each of those decisions. In this paper, I assess which disaggregation strategy delivers the best results for the case of the Chilean 1986–2009 GDP quarterly dataset (base year: 2003). This is done by performing an aggregate-by-disaggregate analysis under different schemes, as the fixed base year dataset allows this fair comparison. The analysis is based on seasonal adjustment diagnostics contained in the X-12-ARIMA program plus some statistical tests for robustness. This exercise is relevant for conjunctural economic assessment, as it concerns signal extraction from seasonal, noisy series, direction of change detection, and econometric applications based on reliable and accurate unobserved variables. The results show that it is preferable, in terms of stability, to use the first block of supply-side disaggregation, while demand-side disaggregation tends to be less reliable. This result carries important implications for policymakers aiming to evaluate its short-term effectiveness in both households and firms.
KeywordsSeasonal adjustment Univariate time-series models ARMA X-12-ARIMA
JEL ClassificationC14 C18 C49 C65 C87
- Astolfi, R., Ladiray, D., & Mazzi, G. L. (2001). Seasonal adjustment of European aggregates: Direct versus indirect approach. Working Document 14 2001, Theme 1 General Statistics, Eurostat.Google Scholar
- Banco Central de Chile. (2010). Cuentas Nacionales de Chile 2003–2009. Available at https://si3.bcentral.cl/estadisticas/Principal1/informes/CCNN/ANUALES/ccnn_2003_2009.pdf.
- Bobbitt, L., & Otto, M. C. (1990). Effects of forecasts on the revisions of seasonally adjusted values using the X-11 seasonal adjustment procedure. In Proceedings of the business and economic statistics section. American Statistical Association (pp. 449–453).Google Scholar
- Di Fonzo, T. (2005). The OECD project on revisions analysis: First elements for discussion. OECD short-term economic statistic expert group report.Google Scholar
- Findley, D. F., Monsell, B. C., Bell, W. R., Otto, M. C., & Chen, B.-C. (1998). New capabilities and methods of the X-12-ARIMA seasonal-adjustment program. Journal of Business and Economic Statistics, 16(2), 127–152.Google Scholar
- Gómez, V., & Maravall, A. (1997). Programs TRAMO and SEATS, instructions for user (Beta Version: September 1996), Working Paper 9628, Bank of Spain.Google Scholar
- Granger, C. W. J. (1979). Seasonality: Causation, interpretation, and implications. In A. Zellner (Ed.), Seasonal analysis of economic time series. New York: National Bureau of Economic Research.Google Scholar
- Hood, C. C. H. (2007). Assessment of diagnostics for the presence of seasonality. In Proceedings of the international conference on establishment surveys III, June 2007.Google Scholar
- Hood, C. C. H., & Findley, D. F. (2001). Comparing direct and indirect seasonal adjustments of aggregate series. In American statistical association proceedings.Google Scholar
- Hood, C. C. H., & McDonald-Johnson, K. M. (2009). Getting started with X-12-ARIMA diagnostics. Catherine Hood Consulting. http://www.catherinechhood.net/papers/gsx12diag.pdf.
- Kendall, M., & Ord, J. K. (1990). Time series (3rd ed.). Oxford: Oxford University Press.Google Scholar
- Ladiray, D., & Mazzi, G. L. (2003). Seasonal adjustment of european aggregates: Direct versus indirect approach. In M. Manna & R. Peronacci (Eds.), Seasonal adjustment. Frankfurt: European Central Bank.Google Scholar
- Lothian, J., & Morry, M. (1978). A set of quality control statistics for the X-11-ARIMA seasonal adjustment method. Research Paper. Statistics CanadaGoogle Scholar
- Maravall, A. (2002). An application of TRAMO-SEATS: Automatic procedure and sectoral aggregation. The Japanese Foreign trade series, Documento de Trabajo 0207, Banco de España.Google Scholar
- Maravall, A. (2005). An application of the TRAMO-SEATS automatic procedure; direct versus indirect adjustment. Documento de Trabajo 0524, Banco de España.Google Scholar
- Medel, C. A. (2014) A Comparison between direct and indirect seasonal adjustment of the Chilean GDP 1986-2009 with X-12-ARIMA. Working Paper 57053, Munich Personal RePEc Archive.Google Scholar
- Otranto, E., & Triacca, U. (2002) A distance-based method for the choice of direct or indirect seasonal adjustment, mimeo. Istituto Nazionale di Statistica, Italy.Google Scholar
- Otto, M. C. (1985). Effects of forecasts on the revisions of seasonally adjusted data using the X-11 seasonal adjustment procedure. In Proceedings of the business and economic statistics section. American Statistical Association (pp. 463–466).Google Scholar
- Peronacci, R. (2003). The seasonal adjustment of euro area monetary aggregates: Direct versus indirect approach. In M. Manna & R. Peronacci (Eds.), Seasonal Adjustment. Frankfurt: European Central Bank.Google Scholar
- Scheiblecker, M. (2014). Direct versus indirect approach in seasonal adjustment. Working Paper 460, Austrian Institute of Economic Research.Google Scholar
- Soukup, R. J., & Findley, D. F. (1999). On the spectrum diagnostics used by X-12-ARIMA to indicate the presence of trading day effects after modeling for adjustment. American Statistical Association Proceedings.Google Scholar
- Stanger, M. (2007). Empalme del PIB y de los Componentes del Gasto: Series Anuales y Trimestrales 1986–2002, Base 2003, Estudio Económico Estadístico 55, Banco Central de Chile.Google Scholar
- US Census Bureau. (2011). X-12-ARIMA reference manual, version 0.3. Available at http://www.census.gov/srd/www/x12/.