Skip to main content

Bayesian Forecasting of Many Count-Valued Time Series

Publication ,  Journal Article
Berry, LR; West, M
Published in: Journal of Business and Economic Statistics
October 1, 2020

We develop and exemplify application of new classes of dynamic models for time series of nonnegative counts. Our novel univariate models combine dynamic generalized linear models for binary and conditionally Poisson time series, with dynamic random effects for over-dispersion. These models estimate dynamic regression coefficients in both binary and nonzero count components. Sequential Bayesian analysis allows fast, parallel analysis of sets of decoupled time series. New multivariate models then enable information sharing in contexts when data at a more highly aggregated level provide more incisive inferences on shared patterns such as trends and seasonality. A novel multiscale approach—one new example of the concept of decouple/recouple in time series—enables information sharing across series. This incorporates cross-series linkages while insulating parallel estimation of univariate models, and hence enables scalability in the number of series. The major motivating context is supermarket sales forecasting. Detailed examples drawn from a case study in multistep forecasting of sales of a number of related items showcase forecasting of multiple series, with discussion of forecast accuracy metrics, comparisons with existing methods, and broader questions of probabilistic forecast assessment.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

Journal of Business and Economic Statistics

DOI

EISSN

1537-2707

ISSN

0735-0015

Publication Date

October 1, 2020

Volume

38

Issue

4

Start / End Page

872 / 887

Related Subject Headings

  • Econometrics
  • 49 Mathematical sciences
  • 38 Economics
  • 35 Commerce, management, tourism and services
  • 15 Commerce, Management, Tourism and Services
  • 14 Economics
  • 01 Mathematical Sciences
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Berry, L. R., & West, M. (2020). Bayesian Forecasting of Many Count-Valued Time Series. Journal of Business and Economic Statistics, 38(4), 872–887. https://doi.org/10.1080/07350015.2019.1604372
Berry, L. R., and M. West. “Bayesian Forecasting of Many Count-Valued Time Series.” Journal of Business and Economic Statistics 38, no. 4 (October 1, 2020): 872–87. https://doi.org/10.1080/07350015.2019.1604372.
Berry LR, West M. Bayesian Forecasting of Many Count-Valued Time Series. Journal of Business and Economic Statistics. 2020 Oct 1;38(4):872–87.
Berry, L. R., and M. West. “Bayesian Forecasting of Many Count-Valued Time Series.” Journal of Business and Economic Statistics, vol. 38, no. 4, Oct. 2020, pp. 872–87. Scopus, doi:10.1080/07350015.2019.1604372.
Berry LR, West M. Bayesian Forecasting of Many Count-Valued Time Series. Journal of Business and Economic Statistics. 2020 Oct 1;38(4):872–887.

Published In

Journal of Business and Economic Statistics

DOI

EISSN

1537-2707

ISSN

0735-0015

Publication Date

October 1, 2020

Volume

38

Issue

4

Start / End Page

872 / 887

Related Subject Headings

  • Econometrics
  • 49 Mathematical sciences
  • 38 Economics
  • 35 Commerce, management, tourism and services
  • 15 Commerce, Management, Tourism and Services
  • 14 Economics
  • 01 Mathematical Sciences