@article{sodja2021detecting,
author = {Sodja, Cole},
title = {Detecting Anomalous Time Series by GAMLSS-Akaike-Weights-Scoring},
year = {2021},
month = {February},
abstract = {An extensible statistical framework for detecting anomalous time series including those with heavy-tailed distributions and nonstationarity in higher-order moments is introduced based on penalized likelihood distributional regression. Specifically, generalized additive models for location, scale, and shape are used to infer sample path representations defined by a parametric distribution with parameters comprised of basis functions. Akaike weights are then applied to each model and time series, yielding a probability measure that can be effectively used to classify and rank anomalous time series. A mathematical exposition is also given to justify the proposed Akaike weight scoring under a suitable model embedding as a way to asymptotically identify anomalous time series. Studies evaluating the methodology on both multiple simulations and a real-world dataset also confirm that anomalies can be detected with high accuracy. Both code implementing the algorithm for running on a local machine and the datasets referenced in this article are available online.},
url = {http://approjects.co.za/?big=en-us/research/publication/detecting-anomalous-time-series-by-gamlss-akaike-weights-scoring/},
pages = {1-13},
journal = {Journal of Computational and Graphical Statistics},
}