Comparative between Multiple Linear Regression and autoregressive integrated moving average in BOVESPA index

Comparação entre o modelo regressão linear multivariada e média móvel autorregressivo no índice BOVESPA

Autores

Bruno Cardoso Universidade do Estado da Bahia
Jéssica Figuera Oliveira Universidade do Estado da Bahia https://orcid.org/0000-0002-1217-9146
Paulo Vinícius Senna Figueiredo Universidade do Estado da Bahia https://orcid.org/0009-0004-7094-8232
Elaine Pereira Garrído Universidade do Estado da Bahia https://orcid.org/0009-0008-1722-1404
José Roberto de Araújo Fontoura Universidade do Estado da Bahia https://orcid.org/0000-0002-9703-835X
Roberto Luiz Souza Monteiro Centro Universitário SENAI CIMATEC https://orcid.org/0000-0002-3931-5953
Alexandre do Nascimento Silva Universidade Estadual de Santa Cruz: Ilheus https://orcid.org/0000-0001-7436-8818

Palavras-chave:

BOVESPA index, Multivariate Linear Regression, Autoregressive Moving Average

Resumo

The present work investigates the results achieved by the Multivariate Linear Regression and Autoregressive Moving Average model based on data from the BOVESPA Index, the selected period of the BOVESPA index is from January 1, 2013, to December 31, 2023. It was observed, by results that there is a need for more in-depth studies on the use of these two methodologies and continuous observation and monitoring of the BOVESPA index, which was created more than 50 years ago, in 1968 and represents the Brazilian stock thermometer and aims to evaluate the performance of the most tradable assets. We assumed the existence of a more efficient model, but after applying them to the same database it was possible to observe the results of the two techniques and compare the statistical errors, thereby finding the most accurate one. We understand that the relevance of the work is based on the presentation of the model that best fits the results of the BOVESPA index. We also understand that other techniques can and should be used in order to find better results.

Downloads

Não há dados estatísticos.

Referências

BARHMI, S.; ELFANTNI, O.; BELHAJ, I. (2020). Forecasting of wind speed using multiple linear regression and artificial neural networks. Energy Systems, 111, 935-946, 2020.

B3. Índice Bovespa. Ibovespa B3. Disponível em: < https://www.b3.com.br/pt_br/market-data-e-indices/indices/indices-amplos/ibovespa.htm />. Acesso em: 27 Fev. 2024.

CAETANO, M. A. L. Python e o mercado financeiro: programação para estudantes, investidores e analistas. 2021.

GE, Y.; WU, H. Prediction of corn price fluctuation based on multiple linear regression analysis model under big data. Neural Computing and Applications, 32, 16843-16855, 2020.

SCHAFFER, A. L.; DOBBINS, T. A.; PEARSON, S. A. Interrupted time series analysis using autoregressive integrated moving average (ARIMA) models: a guide for evaluating large-scale health interventions. BMC medical research methodology, 21(1), 1-12, 2021.

PREACHER, K. J.; CURRAN, P. J.; BAUER, D. J. Computational tools for probing interactions in multiple linear regression, multilevel modeling, and latent curve analysis. Journal of educational and behavioral statistics, 31(4), p. 437-448, 2006.