Time Series Methodology as an analysis tool in chicken production in Brazil

Authors

  • Denise de Assis Paiva Mestranda em Estatística e Experimentação Agropecuária do Departamento de Estatística Universidade Federal de Lavras https://orcid.org/0000-0002-5663-0779
  • Ana Claudia Festucci Herval Doutoranda em Estatística e Experimentação Agropecuária do Departamento de Estatística Universidade Federal de Lavras https://orcid.org/0000-0002-3367-3565
  • Thelma Sáfadi Professora Titular Departamento de Estatística Universidade Federal de Lavras

Keywords:

Time series, broiler slaughter, Box & Jenkins models

Abstract

The present study presents the analysis of the broiler slaughter series (quantity) from 2000 to 2018. This study is relevant since Brazil is the second largest producer of chicken meat in the world. A useful methodology to analyze these data is the analysis of time series, where it can be verify the increase or decrease of the slaughter over time, adjust models and make satisfactory predictions. For this analysis, the additivity of the model, as the presence of trend and seasonal components are verificated. Modeling of the SARIMA (Seasonal ARIMA) class was used. The models considered adequate to the series were compared through the prediction loss functions, the Mean Prediction Error and the Mean Absolute Percentual Error and for the information criteria. It was observed that the number of broiler slaughter presented a growth (apparently linear) by then, starting in 2016, began to decline. In fact, the forecast for 2019 has confirmed that the values tend to decrease. 

References

ABPA. Associação Brasileira de Proteína Animal. Relatório anual 2018. 176p, 2018.Disponível em: < http://abpa-br.com.br/storage/files/relatorio-anual-2018.pdf > . Acesso em 18 de março de 2019.

AKAIKE, H. A new look at the statistical model identification. IEEE Transactions on Automatic Control, AC-19, 716-723, 1974.

BOX, G. E. P.; JENKINS, G. M. Time Series Analysis: Forecasting and Control. San Francisco: HoldenDay, 1970 (Revised edition, 1976).

COTTRELL, A.; LUCCHETTI, R. Gnu Regression, Econometrics and Time-series Library. Disponível em: < http://gretl.sourceforge.net/pt.html >. Acesso em 18 de março de 2019.

GAYA, L.G. et al. Heritability and genetic correlations estimates for performance, carcass and body composition traits in a male broiler line. Poultry Science. v. 85, p. 837-843, 2006.

HANNAN, E. J.; QUINN, B. G. The determination of the order of autoregression. Journal of the Royal Statistical Society, Series B, 41, 190-195, 1979.

Ipeadata. Instituto de Pesquisa Econômica Aplicada. Disponível em: <http://ipeadata.gov.br/beta3/#/dados-serie?anomapa=&ascOrder=&base=macro&busca=&columnOrdering=&end=2018&fonte=&serid=ABATE12_ABQUFR12&skip=0&start=2000&tema=Produ%C3%A7%C3%A3o&territoriality=>. Acesso em 18 de março de 2019.

JENKINS, G.M. Practical Experiences with Modelling and Forecasting Time Series. Jersey, Channel Islands: GJP Publications, 1979.

LJUNG, G. M.; BOX, G. E. P. On a measure of lack of fit in time series models. Biometrika, v.65, p 297-303, 1978.

MORETTIN, P. A.; TOLOI, C. M. C. Análise de Séries Temporais. 2a ed. São Paulo: E. Blucher, 2006, 538p.

R Core Team (2018). R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. URL https://www.R-project.org/.

SCHWARZ, G. Estimating the dimension of a model. Annals of Statistics, 6, 461-464, 1978.

Published

29-07-2019

How to Cite

de Assis Paiva, D., Festucci Herval, A. C., & Sáfadi, T. (2019). Time Series Methodology as an analysis tool in chicken production in Brazil. Sigmae, 8(2), 227–237. Retrieved from https://publicacoes.unifal-mg.edu.br/revistas/index.php/sigmae/article/view/978