Language

Sigmae

e-ISSN: 2317-0840


Vol. 13 Issue 2 (2024) / Applied Statistics

Probabilistic modeling of the IPCA12 index

Luciano Gonçalves Batista Samantha Gouvêa Oliveira Eduardo Campana Barbosa Paulo César Emiliano Maurício Silva Lacerda Kamila Andrade de Oliveira

Author information

Luciano Gonçalves Batista

https://orcid.org/0000-0001-5785-1568
  • luciano.batista@ufv.br
  • Doutorando no programa de Estatística Aplicada e Biometria - Departamento de Estatística (DET/UFV)
  • Biography not informed.

Author information

Samantha Gouvêa Oliveira

ORCID not informed.
  • samantha.gouvea@ufv.br
  • Doutoranda no programa de Estatística Aplicada e Biometria - Departamento de Estatística (DET/UFV)
  • Biography not informed.

Author information

Eduardo Campana Barbosa

ORCID not informed.

Author information

Paulo César Emiliano

https://orcid.org/0000-0002-1314-9002

Author information

Maurício Silva Lacerda

https://orcid.org/0000-0003-1209-3956
  • mauriciolacerda57@gmail.com
  • Docente do Departamento de Apoio ao Ensino - Instituto Federal de Educação, Ciência e Tecnologia de Rondônia (DAPE/IFRO)
  • Biography not informed.

Author information

Kamila Andrade de Oliveira

https://orcid.org/0000-0002-6401-4132
  • kamillarbr@gmail.com
  • Docente do Departamento de Engenharia Agrícola, Campus Chapadinha (DEA/UFMA).
  • Biography not informed.

Published in August 21, 2024 https://10.29327/2520355.13.2-3

Abstract

The objective of this work was to fit a distribution to the IPCA12 dataset and estimate the probability of this index remaining within the confidence limits established by the Central Bank of Brazil for year 2024, which are 3% +- 1.5%. To choose between the log-normal, Gamma, and Weibull distributions, Kolmogorov-Smirnov test, and the Akaike Information Criterion (AIC) were analyzed. The Gamma model with parameters alfa 5.81 and beta 1.09 was selected, and it was estimated that the probability of the true value of IPCA staying within the confidence interval established by the Central Bank for the year 2024 would be 25.45%. Furthermore, maintaining a margin of +- 1.5%, it was possible to conclude that the IPCA value or target that would maximize coverage of the range should be 5.4% instead of 3%. More specifically: P(5.4% - 1.5% <= IPCA12 <= 5.4% + 1.5%) = 45.94%.

References

  • AKAIKE, H. A new look at the statistical model identification. IEEE Transactions on
  • Automatic Control, Notre Dame, v. 19, n. 6, p. 717-723, 1974.
  • BARROS, R. P. de; NERI, M. M., R. Pobreza e inflação no Brasil: Uma análise agregada.
  • Economia Brasileira em Perspectiva. Rio de Janeiro: IPEA, vol 1, 1996. 838 p.
  • CONOVER, W. J. Practical Nonparametric Statistical. John Wiley & Sons Inc., New York,
  • p.
  • DELFIM NETTO, A. Sobre as metas inflacionárias. Revista de Economia Aplicada, v. 3, n. 3,
  • EMILIANO, P. C.; VIVANCO, M. J. F.; MENEZES, F. S. Information criteria: How do they
  • behave in different models?. Computational Statistics & Data Analysis, v. 69, p. 141-153, 2014.
  • FERREIRA, T. P.; FIGUEIREDO F. M. R. Os preços administrados e a inflação no Brasil.
  • Banco Central do Brasil Trabalhos para Discussão, n. 59, Brasília, dez. 2002.
  • FERREIRA, T.P.; PETRASSI,M. B. S. Regime de metas de inflação: resenha sobre a
  • experiência internacional. Banco Central do Brasil. Notas Técnicas, no 30, Brasília, nov., 2002.
  • MARSAGLIA G., TSANG W. W., WANG J. Evaluating Kolmogorov’s distribution. Journal of
  • Statistical Software, v. 8, n. 18, 2003.
  • MILLER, R. B. Maximum likelihood estimation and inference: with examples in R, SAS, and
  • ADMB. 1. ed. [S.l.]: Wiley, 2011.
  • MOOD, A. M.; GRAYBILL, F. A.; BOES, D. C. Introduction to the theory of statistics.
  • Singapore: McGraw-Hill, 1974. 564 p.
  • R CORE TEAM. R: a language and environment for statistical computing. R Foundation for
  • Statistical Computing, Vienna, Austria. 2023.

Paper information

History

  • Received: 18/03/2024
  • Published: 21/08/2024