Shrinkage estimators of time series seasonal factors and their effect on forecasting accuracy

By Don Miller, Daniel W. Williams. 2003

68 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Management Science and Operations Research

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

Citations in the corpus

Forecasting with a hybrid method utilizing data smoothing, a variation of the Theta method and shrinkage of seasonal factors (2018, methodology): “Finally, to further improve the performance of each model, the shrinkage estimators of time series seasonal factors of Miller and Williams (2003) are considered when seasonally adjusting the time series. This is done given that the literature strongly indicates the beneficial effect of shrinkage est”
Reproducibility in forecasting research (2015, methodology): “The results for ‘All 55 series’ are shown to three decimal places, for consistency of presentation with Table 6 of Miller & Williams (2003).”
'Horses for Courses' in demand forecasting (2014, methodology): “The generation procedure assumes a deterministic, multiplicative model where each component is applied individually as suggested by Miller and Williams (2003), but in addition we introduce a cycle component as well.”
Findings from Evidence-Based Forecasting: Methods for Reducing Forecast Error (2006, unknown): “Miller and Williams (2003, 2004) developed a procedure for damping seasonal factors.”
25 Years of IIF Time Series Forecasting: A Selective Review (2005, background): “Miller & Williams (2003, 2004) showed that greater forecasting accuracy is obtained by shrinking the seasonal component towards zero.”
Analysis of photovoltaic system performance time series: Seasonality and performance loss (2015, methodology): “Generally, CSD is regarded as a simple method of seasonal adjustment [19] as the decomposition is performed with minimal effort and computational needs.”
Optimizing Theta Model for Monthly Data (2013, methodology): “Firstly, there is serious empirical evidence that forecasting accuracy can be improved through better estimation of seasonal indices (Miller and Williams, 2003), which lead to the calculation of a more accurate seasonal adjusted series.”
25 years of time series forecasting (2006, background): “Miller & Williams (2003, 2004) showed that greater forecasting accuracy is obtained by shrinking the seasonal component towards zero.”