Advertisement

Sankhya B

pp 1–25 | Cite as

Bayesian Analysis of Double Seasonal Autoregressive Models

  • Ayman A. AminEmail author
Article
  • 19 Downloads

Abstract

In this paper we use the Gibbs sampling algorithm to present a Bayesian analysis to multiplicative double seasonal autoregressive (DSAR) models, considering both estimation and prediction problems. Assuming the model errors are normally distributed and using natural conjugate and g priors on the initial values and model parameters, we show that the conditional posterior distributions of the model parameters and variance are multivariate normal and inverse gamma respectively, and the conditional predictive distribution of the future observations is a multivariate normal. Using these closed-form conditional posterior and predictive distributions, we apply the Gibbs sampling to approximate empirically the marginal posterior and predictive distributions, enabling us easily to carry out multiple-step ahead predictions. The proposed Bayesian method is evaluated using simulation study and real-world time series dataset.

Keywords and phrases

Multiplicative seasonal autoregressive Multiple seasonality Posterior analysis Predictive analysis MCMC methods Gibbs sampler Internet traffic data 

AMS (2000) subject classification

Primary 37M10 Secondary 62F15 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Notes

References

  1. Amin, A. (2009). Bayesian Inference for Seasonal ARMA Models: A Gibbs Sampling Approach. Master’s Thesis, Statistics Department Faculty of Economics and Political Science, Cairo University, Egypt.Google Scholar
  2. Amin, A. (2017a). Bayesian Inference for Double SARMA Models. Communications in Statistics: Theory and Methods.  https://doi.org/10.1080/03610926.2017.1390132.
  3. Amin, A. (2017b). Bayesian inference for double seasonal moving average models: A Gibbs sampling approach. Pak. J. Stat. Oper. Res. 13, 3, 483–499.MathSciNetCrossRefGoogle Scholar
  4. Amin, A. (2017c). Gibbs sampling for double seasonal ARMA models. In: Proceedings of of the 29th Annual International Conference on Statistics and Computer Modeling in Human and Social Sciences, Egypt.Google Scholar
  5. Amin, A. (2017d). Identification of double seasonal autoregressive models: a bayesian approach. In: Proceedings of the 52nd Annual International Conference of Statistics, Computer Science and Operations Research, Egypt.Google Scholar
  6. Amin, A. (2017e). Sensitivity to prior specification in Bayesian identification of autoregressive time series models. Pak. J. Stat. Oper. Res. 13, 4, 699–713.MathSciNetCrossRefGoogle Scholar
  7. Amin, A. (2018a). Bayesian Identification of Double Seasonal Autoregressive Time Series Models. Communications in Statistics: Simulation and Computation,  https://doi.org/10.1080/03610918.2018.1458130.
  8. Amin, A. (2018b). Kullback-Leibler Divergence to Evaluate Posterior Sensitivity to Different Priors for Autoregressive Time Series Models. Communications in Statistics: Simulation and Computation,  https://doi.org/10.1080/03610918.2017.1410709.
  9. Amin, A. and Ismail, M. (2015). Gibbs sampling for double seasonal autoregressive models. Communications for Statistical Applications and Methods 22, 6, 557–573.MathSciNetCrossRefGoogle Scholar
  10. Au, T., Ma, G. and Yeung, S. (2011). Automatic Forecasting of Double Seasonal Time Series with Applications on Mobility Network Traffic Prediction. Joint Statistical Meetings, Florida, USA.Google Scholar
  11. Baek, M. (2010). Forecasting hourly electricity loads of South Korea: Innovations state space modeling approach. The Korean Journal of Economics 17, 2, 301–317.Google Scholar
  12. Box, G., Jenkins, G., Reinsel, G. and Ljung, G. (2016). Time Series Analysis, Forecasting and Control. Wiley, Hoboken.zbMATHGoogle Scholar
  13. Broemeling, L.D. (1985). Bayesian analysis of linear models. CRC Press.Google Scholar
  14. Broemeling, L.D. and Shaarawy, S. (1984). Bayesian inferences and forecasts with moving average processes. Communications in Statistics: Theory and Methods 13, 1871–1888.MathSciNetCrossRefGoogle Scholar
  15. Broemeling, L.D. and Shaarawy, S. (1988). Time series: a bayesian analysis in time domain. Marcel Dekker, New York, spall, J. (ed.),.Google Scholar
  16. Cortez, P., Rio, M., Rocha, M. and Sousa, P. (2012). Multi-scale internet traffic forecasting using neural networks and time series methods. Expert. Syst. 29, 2, 143–155.Google Scholar
  17. Cruz, A., Munoz, A., Zamora, J.L. and Espinola, R (2011). The effect of wind generation and weekday on Spanish electricity spot price forecasting. Electr. Power Syst. Res. 81, 10, 1924–1935.CrossRefGoogle Scholar
  18. Fernandez, C., Ley, E. and Steel, M. (2001). Benchmark priors for Bayesian model averaging. J. Econ. 100, 2, 381–427.MathSciNetCrossRefzbMATHGoogle Scholar
  19. Geweke, J. (1992). Evaluating the accuracy of sampling-based approaches to the calculations of posterior moments. Clarendon Press, Oxford, Bernardo, J. M., Berger, J. O., Dawid, A. P. and Smith, A. F. M. (eds.),.Google Scholar
  20. Ismail, M. and Amin, A. (2014). Gibbs sampling for SARMA models. Pakistan Journal of Statistics 30, 2, 153–168.MathSciNetGoogle Scholar
  21. Kim, M.S. (2013). Modeling special-day effects for forecasting intraday electricity demand. Eur. J. Oper. Res. 230, 1, 170–180.CrossRefGoogle Scholar
  22. Laing, W. and Smith, D. (1987). A comparison of time series forecasting methods for predicting the CEGB demand. In: Proceedings of the Ninth Power Systems Computation Conference.Google Scholar
  23. Mohamed, N., Ahmad, M. and Suhartono, S. (2011). Forecasting short term demand using double seasonal ARIMA model. World Appl. Sci. J. 13, 27–35.Google Scholar
  24. Raftrey, A.E. and Lewis, S. (1995). The number of iterations, convergence diagnostics and generic metropolis algorithms. Chapman and Hall, London, Gilks, W. R., Spiegelhalter, D. J. and Richardson, S. (eds.),.Google Scholar
  25. Shaarawy, S. and Ali, S. (2003). Bayesian identification of seasonal autoregressive models. Communications in Statistics: Theory and Methods 32, 5, 1067–1084.MathSciNetCrossRefzbMATHGoogle Scholar
  26. Taylor, J.W., De Menezes, L.M. and McSharry, P. (2006). Comparison of univariate methods for forecasting electricity demand up to a day ahead. Int. J. Forecast. 22, 1–16.CrossRefGoogle Scholar
  27. Taylor, J.W. (2008a). An evaluation of methods for very short-term load forecasting using minute-by-minute British data. Int. J. Forecast. 24, 645–658.CrossRefGoogle Scholar
  28. Taylor, J.W. (2008b). A Comparison of univariate time series methods for forecasting intraday arrivals at a call center. Manag. Sci. 54, 253–265.CrossRefzbMATHGoogle Scholar
  29. Thompson, H. and Tiao, G. (1971). Analysis of telephone data. Bell J. Econ. Manag. Sci. 2, 514–541.CrossRefGoogle Scholar

Copyright information

© Indian Statistical Institute 2019

Authors and Affiliations

  1. 1.Department of Statistics, Mathematics, and Insurance, Faculty of CommerceMenoufia UniversityMenoufiaEgypt

Personalised recommendations