The use of a Detrended Cross-Correlation Analysis on returns from agricultural commodities in the subprime crisis

Luiza Lonardoni Paulino Schiavon; Antonio Fernando Crepaldi

doi:10.15675/gepros.v16i3.2795

Autores

Luiza Lonardoni Paulino Schiavon https://orcid.org/0000-0002-2816-2728
Antonio Fernando Crepaldi https://orcid.org/0000-0002-9090-1835

DOI:

https://doi.org/10.15675/gepros.v16i3.2795

Palavras-chave:

Crise Financeira do Subprime, Commodities Agrícolas, Detrended Fluctuation Analysis, Detrended Cross-Correlation Analysis

Resumo

Purpose: To understand the dynamics of the agricultural commodities market and predict a possible economic crisis, in addition to helping agricultural producers balance their product portfolio, diversifying their goods and reducing risks.
Theoretical framework: Prices of agricultural commodities have changed significantly since 2002; although had been an increase in demand, where weather problems negatively affected supply, resulting in price increases. With the global financial crisis of 2008, there was a reduction in international credit and an increase in the US dollar against the Brazilian Real.
Design/Methodology/Approach: Detrended Cross-Correlation Analysis and Detrended Fluctuation Analysis methods were used to understand the behavior of the cross correlations of the price of five Brazilian agribusiness commodities (cotton, sugar, coffee, corn and soybeans) for the previous periods, during and after the subprime crisis.
Findings: Both methods showed a significant change in the behavior of the series in the period of crisis, when compared to their temporal neighborhoods.
Research, Practical & Social Implications: It was found that the crisis changed the structure of the correlation of the returns on the commodities analyzed. This change implies alterations to a possible product portfolio in order to minimize risks.
Originality/Value: The long-term nonlinear correlation behavior was calculated and analyzed on the temporal series for the return on the main agricultural commodities in the period of the subprime crisis and its temporal neighborhoods were calculated and analyzed, allowing several changes to be found in the product correlation structure, due to the crisis process.
Keywords: Subprime Financial Crisis; Agricultural Commodities; Detrended Fluctuation Analysis; Detrended Cross-Correlation Analysis.

Referências

ABE, Mirian Mayumi. A Crise de 2008 e Seu Impacto em Países Economicamente Dependentes de commodities. 38 f. Dissertação (Mestrado) - Curso de Economia, Fundação Getúlio Vargas, São Paulo, 2011.

CARVALHO, F. C. Entendendo a Recente Crise Financeira Global. 2008. Disponível em: http://docplayer.com.br/11990329-Entendendo-a-recente-crise-financeira-global.html. Acesso em: 20 dez. 2018.

CEPEA. 2018. Disponível em: https://cepea.esalq.usp.br/br. Acesso em: 18 abr. 2018.

CREPALDI, A.F. Abordagem de Modelos Baseados em Agentes no Estudo de Séries Temporais Financeiras. Universidade Estadual Paulista Júlio de Mesquita Filho, UNESP, São Paulo, 2007.

EHLERS, Ricardo S. Análise de séries temporais.Curitiba: Laboratório de Estatística e Geoinformação, Universidade Federal do Paraná, 2007.

EMBRAPA SOJA. Soja em Números (safra 2019/2020). Disponível em https://www.embrapa.br/soja/cultivos/soja1/dados-economicos Acesso em 06.01.2021

GUTH, T. L. F. Análise Mensal. Milho (junho/julho de 2019). CONAB. Disponível em file:///D:/Downloads/MilhoZ-ZAnaliseZZMensalZ-ZJunho-Julho-2019.pdf. Acesso em 06.01.2021.

KOSCIELNY-BUNDE, E.; BUNDE, A.; HAVLIN, S.; ROMAN, H. E.. Indication of a universal persistence law governing atmospheric variability. Physical Review Letters, v. 81, n. 3, p. 729, 1998. DOI: https://doi.org/10.1103/PhysRevLett.81.729

KRISTOUFEK, L. Measuring cross-correlation between non-stationary series with DCCA coefficient. Physica A, v. 402, p. 291–298, 2014. DOI: https://doi.org/10.1016/j.physa.2014.01.058

JALE, J. S. commodities agrícolas do agronegócio brasileiro: análise multifractal e análise da complexidade diante da crise financeira mundial subprime 2008/2009. Tese de Doutorado. Universidade Federal Rural de Pernambuco, Recife, 2015.

MARINHO, E. B. S., SOUSA, A. M. Y. R., ANDRADE, R. F. S. Using Detrended Cross- Correlation Analysis in Geophysical Data, Physica A 392, 2195-220, 2013. DOI: https://doi.org/10.1016/j.physa.2012.12.038

MINISTÉRIO DA AGRICULTURA. Balança Comercial - Série Histórica (1997-2017). 2017. Disponível em: <http://www.agricultura.gov.br/assuntos/relacoes-internacionais/estatisticas-de-comercio-exterior> Acesso em: 20 dez. 2018.

MORETTIN, P.A.; TOLOI, C.M.C. Análise de Séries Temporais, ABE - Projeto Fisher. Editora Edgard Blucher LTDA, São Paulo, 2004.

PENG, C.K. HAVILIN, S., STANLEY, H.E., GOLDBERGER, A.L. On the mosaic organization of DNA sequences. Physical Review E, n. 49, p. 1685-1689, 1994. DOI: https://doi.org/10.1103/PhysRevE.49.1685

PENG, C.‐K. et al. Quantification of scaling exponents and crossover phenomena in nonstationary heartbeat time series. Chaos: an interdisciplinary journal of nonlinear science, v. 5, n. 1, p. 82-87, 1995. DOI: https://doi.org/10.1063/1.166141

PODOBNIK, B., STANLEY H.E, Detrended cross- correlation analysis: A new method for analyzing two non-stationary time series. Phys. Rev. Let, v. 100, p .084102, 2008. DOI: https://doi.org/10.1103/PhysRevLett.100.084102

PODOBNIK, B.; JIANG, Z.Q.; ZHOU, W.X.; STANLEY H.E. Statistical tests for power-law cross-correlated processes. Phys. Rev. E, v. 84, p. 066118, 2011. DOI: https://doi.org/10.1103/PhysRevE.84.066118

SHAHBANDEH, M. Global sugar production by leading conuntry 2019/2020. STATISTA, 2019. Disponível em https://www.statista.com/statistics/495973/sugar-production-worldwide/#:~:text=This%20statistic%20shows%20the%20sugar,million%20metric%20tons%20of%20sugar Acesso em 06.01.2021.

SEVERINO, L S et al. Série Desafios do agronegócio Brasileiro (NT3). Produto: Algodão – Parte 01: Caracterização e Desafios Tecnológicos. EMBRAPA, 2019. Disponível em https://ainfo.cnptia.embrapa.br/digital/bitstream/item/198192/1/SerieDesafiosAgronegocioBrasileiroNT3Algodao.pdf. Acesso em 06/01/2021.

SILVA, Diego Roberto Cintra da. Utilização do Dentreded Fluctuation Analysis e do Dentreded Cross-Correlation Analysis para estudo do espectro de correlação de ações constantes no Ibovespa no período de crise do subprime. 2017. 88 f. Dissertação (Mestrado) - Curso de Engenharia de Produção, Universidade Estadual Paulista, Unesp, Bauru, 2017.

SILVA FILHO, A. Correlação de Longo Alcance em Indicadores de Criminalidade de Salvador – BA: DFA E DCCA. Dissertação de Mestrado. Faculdade de Tecnologia Senai Cimatec, Salvador, 2009.

SIQUEIRA JÚNIOR, E.L.; BEJAN, L.B.; STOSIC, T. Comparando produtos agropecuários e ações no mercado brasileiro usando Detrended Fluctuation Analysis em séries históricas de preços. In: VIII Encontro regional de matemática aplicada e computacional, Natal, 2008.

SIQUEIRA JÚNIOR, E.L.; STOSIC, T.; BEJAN, L.B.. Correlations and cross-correlation in the brazilian agrarian commodities and stocks. Physica A, n. 14, v. 389, p. 2739-2743, 2010. DOI: https://doi.org/10.1016/j.physa.2010.01.040

URSULEAN, R; LAZAR, A.M. Detrended Cross-Correlation Analysis of Biometric Signals used in a new Authentication Method. In: The 13th International Conference Electronics and Electrical Engineering, Lithuania, 2009.

UNITED STATES DEPARTAMENT OF AGRICULTURE (USDA). Coffee: World Markets and Trade. 2019/2020 forecast review, 2019. Disponível em https://downloads.usda.library.cornell.edu/usda-esmis/files/m900nt40f/sq87c919h/8w32rm91m/coffee.pdf. Acesso em 06.01.2021.

WANG, G.; XIE, C.; CHEN, S.; YANG, J.; YANG, M.J.W. Random matrix theory analysis of cross-correlations in the US stock market: Evidence from Pearson’s correlation coefficient and detrended cross-correlation coefficient. Physica A n.17, v. 392, p. 3715–3730, 2013. DOI: https://doi.org/10.1016/j.physa.2013.04.027