Journal article
The tensor auto-regressive model
Journal of forecasting, v 40(4), pp 636-652
01 Jul 2021
Abstract
We introduce the tensor auto-regressive (TAR) model for modeling time series data, which is found to be robust to model misspecification, seasonality, and nonlinear trends. We develop a parameter estimation algorithm for the proposed model by using the -product, which allows us to model a three-dimensional block of parameters. We use the fast Fourier transform, which allows for efficient and parallelizable computation. We use a combination of simulated data and an empirical application to: (i) validate the model, including seasonal and geometric trends, model misspecification analysis, and bootstrapping to compute standard errors; (ii) present model selection results; and (iii) demonstrate the performance of the proposed model against benchmarking and competitive forecasting methods. Our results indicate that our model performs well against comparable methods and is robust and computationally efficient.
Metrics
Details
- Title
- The tensor auto-regressive model
- Creators
- Chelsey Hill - Drexel UniversityJames Li - FacebookMatthew J. Schneider - Drexel UniversityMartin T. Wells - Cornell University
- Publication Details
- Journal of forecasting, v 40(4), pp 636-652
- Publisher
- Wiley
- Number of pages
- 17
- Resource Type
- Journal article
- Language
- English
- Academic Unit
- Decision Sciences (and Management Information Systems)
- Web of Science ID
- WOS:000591841300001
- Scopus ID
- 2-s2.0-85096746531
- Other Identifier
- 991019168290904721
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- Industry collaboration
- Domestic collaboration
- Web of Science research areas
- Economics
- Management