Detecting time series outliers
The tsoutliers() function in the forecast package for R is useful for identifying anomalies in a time series. However, it is not properly documented anywhere. This post is intended to fill that gap. The function began as an answer on CrossValidated and was later added to the forecast package because I thought it might be useful to other people. It has since been updated and made more reliable.Forecasting: Principles and Practice
Recent papers
- George Athanasopoulos, Rob J Hyndman, Nikolaos Kourentzes, Mitchell O'Hara‑Wild (2021) Probabilistic forecasts using expert judgement: the road to recovery from COVID-19. Journal of Travel Research, to appear. Abstract pdf
- Hansika Hewamalage, Pablo Montero-Manso, Christoph Bergmeir, Rob J Hyndman (2021) A Look at the Evaluation Setup of the M5 Forecasting Competition. Abstract pdf
- Kasun Bandara, Rob J Hyndman, Christoph Bergmeir (2021) MSTL: A Seasonal-Trend Decomposition Algorithm for Time Series with Multiple Seasonal Patterns. Abstract pdf
- Evangelos Spiliotis, Mahdi Abolghasemi, Rob J Hyndman, Fotios Petropoulos, Vassilios Assimakopoulos (2021) Hierarchical forecast reconciliation with machine learning. Applied Soft Computing, 112, 107756. Abstract DOI pdf
- Atefeh Zamani, Hossein Haghbin, Maryam Hashemi, Rob J Hyndman (2021) Seasonal functional autoregressive models. J Time Series Analysis, to appear. Abstract DOI pdf
Recent and upcoming seminars
- Feasts & fables: Time series analysis using R. (28 September 2021) More info...
- The geometry of forecast reconciliation. (16 September 2021) More info...
- GRATIS: GeneRAting TIme Series with diverse and controllable characteristics. (10 September 2021) YouTube More info...
- Uncertain futures: what can we forecast and when should we give up?. (17 August 2021) YouTube More info...
- Probabilistic ensemble forecasting of Australian COVID-19 cases. (29 June 2021) YouTube More info...