The theta model: a decomposition approach to forecasting

By Vassilios Assimakopoulos, Konstantinos Nikolopoulos. 2000

505 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Management Science and Operations Research, Time-Series & Forecasting

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

In Management Science and Operations Research

In Time-Series & Forecasting

Citations in the corpus

N-BEATS: Neural basis expansion analysis for interpretable time series forecasting (2019, methodology): “More advanced variations of exponential smoothing include the winner of M3 competition, the Theta method [2] that decomposes the forecast into several theta-lines and statistically combines them.”
Forecasting with a hybrid method utilizing data smoothing, a variation of the Theta method and shrinkage of seasonal factors (2018, methodology): “In order for a newly proposed forecasting approach to have any credibility and claim that it can stand the test of time, it should compete favorably and beat the two best established benchmarks in the field: Damped Trend Exponential smoothing (Gardner and McKenzie, 1985) and the Theta method (Assima”
The Tourism Forecasting Competition (2011, methodology): “This method was arguably the most accurate for seasonal data and was second only to the Theta method (Assimakopoulos and Nikolopoulos, 2000) for non-seasonal data.”
Fathoming the theta method for a unit root process (2014, result): “These results extend earlier work by Assimakopoulos and Nikolopoulos (2000) and Hyndman and Billah (2003) and can potentially explain the very good performance of the theta method in the M3 forecasting competition.”
Predictability of monthly temperature and precipitation using automatic time series forecasting methods (2018, methodology): “Recent methods for automatic time series forecasting that have been used rarely in hydrology include the Theta method (Assimakopoulos and Nikolopoulos 2000; Hyndman and Billah 2003) and the BATS (acronym for Box–Cox transformation, ARMA errors, Trend and Seasonal components) method (De Livera et…”
The inventory performance of forecasting methods: Evidence from the M3 competition data (2019, methodology): “We also include in our pool the standard version of the Theta method, as proposed by Assimakopoulos and Nikolopoulos (2000). The Theta method is a data-decomposition approach that attempts to separate the short term movements from the long-term trend of the data. Hyndman and Billah (2003) and Fioruc”
Electricity price forecasting: A review of the state-of-the-art with a look into the future (2014, methodology): “An interesting variant of exponential smoothing is the so-called THETA method of Assimakopoulos and Nikolopoulos (2000). Hyndman and Billah (2003) demonstrate that it is equivalent to simple exponential smoothing with drift, where the drift is half the value of the slope of a linear regression fitte”
Visualising forecasting algorithm performance using time series instance spaces (2017, methodology): “Commentaries on the M3-Competition.”
Optimizing Theta Model for Monthly Data (2013, methodology): “The original Theta model (Assimakopoulos and Nikolopoulos, 2000) introduced a unique decomposition of the original time series into two separate lines, the so called “Theta Lines”.”
Forecasting model selection through out-of-sample rolling horizon weighted errors (2011, methodology): “…use mathematical programming to establish their parameters: • Decomposition models: classical additive or multiplicative decomposition; Theta Model (Assimakopoulos & Nikolopoulos, 2000) • Exponential Smoothing Models: Simple smoothing; Holt (Holt et al., 1960); HoltWinter (additive or…”