Modeling count time series

a comparative case study

Authors

Keywords:

Observation-driven model, Parameter-driven model, GAM-ARMA, NGSSEML, counting data

Abstract

This paper presents an application for counting data, where the observation-driven and parameter-driven models are compared. To this purpose, the Generalized Additive Autoregressive Moving Average (GAM-ARMA) and Non-Gaussian State Space with Exact Marginal Likelihood (NGSSEML) models are used. Model parameters are estimated using the maximum likelihood method. The ability of the procedure to model and forecast real data is presented for the number of chronic obstructive disease (COPD) cases.

Author Biographies

Gisele de Oliveira Maia, Federal University of Minas Gerais

Statistics Department

Glaura da Conceição Franco , Federal University of Minas Gerais

Statistics Department

Thiago Rezende dos Santos , Federal University of Minas Gerais

Statistics Department

Ana Júlia Alves Câmara , Federal University of Espirito Santo

Statistics Department

References

O. Y. E. Albarracin, A. P. Alencar, and L. L. Ho. Generalized autoregressive and moving average

models: multicollinearity, interpretation and a new modified model. Journal of Statistical

Computation and Simulation, 89(10):1819–1840, 2019.

M. A. Benjamin, R. A. Rigby, and D. M. Stasinopoulos. Generalized autoregressive moving

average models. Journal of the American Statistical association, 98(461):214–223, 2003.

A. J. A. Camara, G. C. Franco, V. A. Reisen, and P. Bondon. Generalized additive model for

count time series: An application to quantify the impact of air pollutants on human health.

Pesquisa Operacional, 41, 2021.

D. R. Cox. Statistical analysis of time series: Some recent developments. Scandinavian Journal

of Statistics, pages 93–115, 1981.

R. A. Davis and H. Liu. Theory and inference for a class of observation-driven models with

application to time series of counts. arXiv preprint arXiv:1204.3915, 2012.

R. A. Davis and R. Wu. A negative binomial model for time series of counts. Biometrika, 96

(3):735–749, 2009.

R. A. Davis, W. T. Dunsmuir, and Y. Wang. Modeling time series of count data. Statistics

textbooks and monographs, 158:63–114, 1999.

R. A. Davis, W. T. Dunsmuir, and Y. Wang. On autocorrelation in a poisson regression model.

Biometrika, 87(3):491–505, 2000.

R. A. Davis, W. T. Dunsmuir, and S. B. Streett. Observation-driven models for poisson counts.

Biometrika, 90(4):777–790, 2003.

C. De Boor. A practical guide to splines, volume 27. springer-verlag New York, 1978.

G. de Oliveira Maia, W. Barreto-Souza, F. de Souza Bastos, and H. Ombao. Semiparametric

time series models driven by latent factor. International Journal of Forecasting, 37(4):1463–

, 2021.

W. T. Dunsmuir and D. J. Scott. The glarma package for observation-driven time series regres sion of counts. Journal of Statistical Software, 67:1–36, 2015.

P. H. C. Eilers and B. D. Marx. Flexible smoothing with B-splines and penal ties. Statistical Science, 11(2):89 – 121, 1996. doi: 10.1214/ss/1038425655. URL https://doi.org/10.1214/ss/1038425655.

G. C. Franco, H. S. Migon, and M. O. Prates. A monte carlo study and data analysis for

time series of counts. Relat´orio T´ecnico Relat´orio T´ecnico RTP-01/2015, Belo Horizonte:

Departamento de Estatıstica-UFMG, 2015.

J. H. Friedman and B. W. Silverman. Flexible parsimonious smoothing and ad ditive modeling. Technometrics, 31(1):3–21, 1989. ISSN 00401706. URL

http://www.jstor.org/stable/1270359.

D. Gamerman, T. R. dos Santos, and G. C. Franco. A non-gaussian family of state-space models

with exact marginal likelihood. Journal of Time Series Analysis, 34(6):625–645, 2013.

P. J. Green and B. W. Silverman. Nonparametric regression and generalized linear models: a

roughness penalty approach. Crc Press, 1994.

F. E. Harrel. Bioestatistical modeling. Nashvile TN USA, 2004.

T. Hastie and R. Tibshirani. Generalized Additive Models. Chapman & Hall/CRC Monographs

on Statistics & Applied Probability. Taylor & Francis, 1990. ISBN 9780412343902. URL

https://books.google.com.br/books?id=qa29r1Ze1coC.

R. C. Jung and A. R. Tremayne. Useful models for time series of counts or simply wrong ones?

AStA Advances in Statistical Analysis, 95:59–91, 2011.

R. C. Jung, M. Kukuk, and R. Liesenfeld. Time series of count data: modeling, estimation and

diagnostics. Computational Statistics & Data Analysis, 51(4):2350–2364, 2006.

C. Kooperberg and C. J. Stone. A study of logspline density estimation. Computational Statistics

& Data Analysis, 12(3):327–347, 1991.

M. Melo and A. Alencar. Conway–maxwell–poisson autoregressive moving average model for

equidispersed, underdispersed, and overdispersed count data. Journal of Time Series Analysis,

(6):830–857, 2020.

A. V. Rocha and F. Cribari-Neto. Beta autoregressive moving average models. Test, 18:529–545,

S. L. Zeger. A regression model for time series of counts. Biometrika, 75(4):621–629, 1988.

S. L. Zeger and B. Qaqish. Markov regression models for time series: a quasi-likelihood approach.

Biometrics, pages 1019–1031, 1988.

Downloads

Published

20-03-2024 — Updated on 11-04-2024

Versions

How to Cite

Maia, G. de O., Franco , G. da C., Santos , T. R. dos, & Câmara , A. J. A. (2024). Modeling count time series: a comparative case study. Sigmae, 13(1), 13–23. Retrieved from https://publicacoes.unifal-mg.edu.br/revistas/index.php/sigmae/article/view/2274 (Original work published March 20, 2024)