English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

relating the model to a general indicator time series {Jt} (univariate or multivariate, random or deterministic, observable or not) allows to put into the threshold framework a very large class of models, including hidden Markov models and many others that may be plausible and useful in specific applications. I found the suggestion of partially hidden switching models particularly stimulating, and think that it could be developed in various directions with interesting results. I will comment briefly on one of the particularization of (3.1), which is also cited in the paper’s concluding remarks as a possible advancement: non stationary – non linear models. The threshold idea, though originated by cycles, may be easily employed for modeling structural change in time, suggesting autoregressive models where the parameter values change both according to time, in two or more regimes, and according to the value of a previous observation. Essentially, one may think of a model of form (3.1) with the indicator time series given by:

Discussion of “Threshold models in time series analysis — 30 years on” by H. Tong