A Note on Threshold Principle, Artificial Neural Network Connections and Econometric Legacy
Abstract
This is mostly a non-technical note, reflecting the author's philosophy and personal views on time series analysis, with references limited to only a few representatives for brevity. The Threshold Principle, formally announced in Tong (1990), modernised time series analysis by introducing a collection of sub-systems to model complex nonlinear dynamics. We explore the conceptual architecture of the Threshold Principle drawing parallels and contrasts with artificial neural network in machine learning. We trace the influential adoption of Threshold Autoregression in econometrics. We examine a smooth extension, namely the smooth threshold autoregression introduced by Chan and Tong (1986) that was later popularized in the Econometric literature. We sound cautions to help econometric users to avoid misuse of this model. Furthermore, we examine how we can systematically apply the Threshold Principle to conditional variance to enable meaningful volatility classification. Finally, we mention some of the modern applications of the Threshold Principle to non-real-valued domains, underscoring its enduring half-century methodological significance as embodied in the threshold autoregression.
Related
- Econometric Inference for Regularized Riemann-Liouville Fractional Brownian Motion Second-Order Filtering, HAC-GMM, and Weak Identification
- Financial Resilience Under a Major Gold-Price Regime Shift: A Benchmark-Based Assessment of Machine Learning, Deep Learning, and Econometric Models
- Bridging Network Psychometrics and Artificial Intelligence: An Ising-Potts Model with LLM-Derived Weights
- FPGA-Based Implementation of Artificial Neural Network for Accelerated Handwritten Digit Recognition
- A hybrid chemoinformatics approach integrating caputo fractional-derivative graph invariants and artificial neural network for modeling of anti-sickle cell compounds
BibTeX
@misc{tong2026note,
title = {{A Note on Threshold Principle, Artificial Neural Network Connections and Econometric Legacy}},
author = {Howell Tong},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.33247},
eprint = {2609.33247},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.33247},
}
RIS
TY - UNPB
TI - A Note on Threshold Principle, Artificial Neural Network Connections and Econometric Legacy
AU - Howell Tong
PY - 2026
DA - 2026/09/27
PB - arXiv
DO - 10.48550/arxiv.2609.33247
UR - https://arxiv.org/abs/2609.33247
AB - This is mostly a non-technical note, reflecting the author's philosophy and personal views on time series analysis, with references limited to only a few representatives for brevity. The Threshold Principle, formally announced in Tong (1990), modernised time series analysis by introducing a collection of sub-systems to model complex nonlinear dynamics. We explore the conceptual architecture of the Threshold Principle drawing parallels and contrasts with artificial neural network in machine learning. We trace the influential adoption of Threshold Autoregression in econometrics. We examine a smooth extension, namely the smooth threshold autoregression introduced by Chan and Tong (1986) that was later popularized in the Econometric literature. We sound cautions to help econometric users to avoid misuse of this model. Furthermore, we examine how we can systematically apply the Threshold Principle to conditional variance to enable meaningful volatility classification. Finally, we mention some of the modern applications of the Threshold Principle to non-real-valued domains, underscoring its enduring half-century methodological significance as embodied in the threshold autoregression.
ER -