UseR!2018 talks
All talks from useR!2018, held in Brisbane last week, are now available on YouTube.
Links to talks from members of my research team are given below.
Seasonal decomposition of short time series
Many users have tried to do a seasonal decomposition with a short time series, and hit the error “Series has less than two periods”. The problem is that the usual methods of decomposition (e.g., decompose and stl) estimate seasonality using at least as many degrees of freedom as there are seasonal periods. So you need at least two observations per seasonal period to be able to distinguish seasonality from noise.Recent publications
- Alexander Dokumentov, Rob J Hyndman, Leonie Tickle (2018) Bivariate smoothing of mortality surfaces with cohort and period ridges. Stat, to appear. Abstract pdf
- Thiyanga S Talagala, Rob J Hyndman, George Athanasopoulos (2018) Meta-learning how to forecast time series. Abstract pdf
- Bin Jiang, George Athanasopoulos, Rob J Hyndman, Anastasios Panagiotelis, Farshid Vahid (2018) Macroeconomic forecasting for Australia using a large number of predictors. Abstract pdf
- Priyanga Dilini Talagala, Rob J Hyndman, Kate Smith-Miles, Sevvandi Kandanaarachchi and Mario A Muñoz (2018) Anomaly detection in streaming nonstationary temporal data. Abstract pdf
Recent and upcoming seminars
- Tidy forecasting in R. (13 July 2018) More info...
- Forecasting: principles and practice (NYC). (25 June 2018) More info...
- Feature-based time series analysis. (21 June 2018) More info...
- Tidy forecasting in R. (19 June 2018) More info...