Caracterização do comportamento sazonal de séries macroeconômicas por setor no Brasil no contexto da pandemia da COVID-19: Uma análise a partir do método de ajuste sazonal ARIMA X-13 SEATS

Aydano Ribeiro Leite

Aydano Ribeiro Leite UNIVERSIDADE REGIONAL DO CARIRI

Abstract

The year 2020 can be considered a turning point due to the shock of the Covid-19 pandemic and its impacts on the various sectors that make up the Brazilian economy. The need to control and prevent the proliferation of the virus, caused governments around the world to adopt measures of social isolation, which led to the partial paralysis of sectors of the economy resulting in a strong retraction in economic activity. The purpose of this work was to investigate and characterize, in the face of the shock of the Covid-19 pandemic, the seasonal behavior of the macroeconomic series in the industrial, commercial and services sectors, in addition to the level of economic activity expressed in the IBC-br. For this purpose, the analytical method of seasonal adjustment ARIMA X-13 SEATS was used, seeking to identify the Auto-regressive (AR) and Moving Averages (MA) processes, in addition to the possible calendar effects such as the days of the week, commemorative dates and the level shift outliers (LS) or additive outliers (AO) associated with exogenous shocks and impacts related to the Covid-19 pandemic. The results showed significant effects of outliers in relation to the pandemic on the analyzed sectors and the level of activity of the economy in Brazil. In addition, the most significant negative effects were identified in the second quarter of 2020, while as of the second quarter of the same year, there is evidence of a short-term recovery in the economy and the sectors evaluated.

Downloads

Download data is not yet available.

References

Aguirre, A., & Aguirre, L. A. (1999). Modelos estatísticos e econométricos para estudo da sazonalidade de preços: o caso do preço da carne de boi. Nova Economia, 9.
Cavalcanti, M.A.F.H, et al. Atividade Econômica: PIB no Segundo Trimestre de 2020. Carta de Conjuntura. Número 8. Terceiro Trimestre de 2020. IPEA.
Chen, C., Liu, L. (1993a) JOINT ESTIMATION OF MODEL PARAMETERS AND OUTLIER EFFECTS IN TIME SERIES, JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 88, 284-297.
Dell’Ariccia, G., Mauro, P., Spilimbergo, A., and Zettelmeyer, J. (2020) Economic policies for the COVID-19 war, IMFBlog.
Ferreira, et. al. Métodos de ajuste sazonal para séries de Business Tendency: um estudo de caso para a Sondagem da Indústria utilizando o método X13-ARIMASEATS. Fundação Getúlio Vargas, 2015, p.43.
Ferreira, P., Gondin Jr, J., & Mattos, D. M. (2015). Portal IBRE/FGV. Acesso em 2015, disponívelemhttp://portalibre.fgv.br/main.jsp?lumPageId=402880811D8E34B9011D9CCBFDD1784C&contentId=8A 7C82C54ADE6252014B4A982E0662F6.
Ferreira, P.; Mattos, D.M. Usando o R para ensinar Ajuste Sazonal. São Paulo:FGV,2017.18p.Disponívelem: http://portalibre.fgv.br/lumis/portal/file/fileDownload.jsp?fileId=8A7C82C5519A547801533DF7BE5E2D0D
Findley, D.F. et.al (1998), “New Capabilities and Methods of the X- 12-ARIMA Seasonal-Adjustment Program,” Journal of Business and Economic Statistics, 16(2): 127–152.
Fok, D, et.al.Performance of Seasonal Adjustment Procedures: Simulation and Empirical Results. Econometric Institute Report,2005.
Gelper, S, et.al. C. Robust forecasting with exponential and Holt-Winters smoothing. Journal of Forecasting,v.29,285-300, 2010.Disponívelem: https://pure.tue.nl/ws/portalfiles/portal/3954158/671965904247136.pdf
Hannan, E.J; Rissanen, J., 1982. Recursive estimation of mixed autoregressive-moving average order. Biometrika 69, 81–94.
Harvey, A.C. Forcasting, structural time series models and the Kalman filter. Cambridge: Cambridge University Press, 1989.
Harvey, A., & Shephard, N. (1993). Structural Time Series Models. In: Handbook of Statistics (Vol. 11). Elsevier Science Publishers B.V.
Holt, C.C (1957) Forecasting Seasonals and Trends by Exponentially Weighted Moving Averages. ONR Memorandum, vol. 52, Carnegie Institute of Technology, Pittsburgh.
IBGE. Pesquisa Industrial Mensal Produção Física - Brasil. Retrieved in 2020, from http://ibge.gov.br/home/estatistica/indicadores/industria/pimpf/br/default.shtm.
Jorgenson, D.W. (1964). “Minimum variance, linear, unbiased seasonal adjustment of economic time series,” Journal of the American Statistical Association, 59, 681–724.
Lopes, A.C.B.The Robustness of Test for Seasonal Differencing to Structural Breaks. Economic Letters, 71, 173-179.
Maravall, et.al. Reg-arima model identification: empirical evidence. Bank of Spain, 2014, 37 p.
Morettin, P.A; Toli, C.M.C. Previsão de Séries Temporais.Instituto de Matemática Pura e Aplicada (IMPA), (1987), 400p.
Pedersen, M. K., Faeste, C. F. Seasonal adjust of Danish financial time series using the X12-ARIMA procedure. Danmarks Nationalbank, 2006.
Plosser, C.I.. A time series analysis of seasonality in econometric models. The National Bureau of Economic Research, 1979.
Rasmussen, R. (2004). On time series data and optimal parameters. The International Journal of Management Science.
Shiskin, J., A.H. Young, and J.C. Musgrave (1967), “The X-11 Variant of the Census Method II Seasonal Adjust¬ment Program,” Technical Report 15, U.S. Bureau of the Census, Washington, DC.
Tsay, R. S. (1986), TIME SERIES MODEL SPECIFICATION IN THE PRESENCE OF OUTLIERS, JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 81, 132-141
Winters,P.R.(1960).Forecasting sales by exponentially weighted moving averages, Management Science, 6, 324–342.
Zellner. A. Front matter to ‘seasonal analysis of economic time series. The National Bureau of Economic Research, 1979.Box, G., Jenkins, G., Time series analysis, forecasting and control. Holdan Day. Oakland, California, USA, 1976.