IEEE Transactions on Neural Networks and Learning Systems · 2015 · 185 citations · 45 references
BusinessBusiness EconomicsForecastingPredictive AnalyticsTime Series AnalysisForecast Error AnalysisForecast EvaluationForecasting MethodsTime Series ForecastingTime Series ModelingTime Series PredictionForecast Performance EvaluationMonte Carlo AnalysisMonte Carlo ForecastingMulti-step ForecastingMulti-step-ahead ForecastingSimulation StudiesVariance Components Analysis
Multistep-ahead forecasts can either be produced recursively by iterating a one-step-ahead time series model or directly by estimating a separate model for each forecast horizon. In addition, there are other strategies; some of them combine aspects of both aforementioned concepts. In this paper, we present a comprehensive investigation into the bias and variance behavior of multistep-ahead forecasting strategies. We provide a detailed review of the different multistep-ahead strategies. Subsequently, we perform a theoretical study that derives the bias and variance for a number of forecasting strategies. Finally, we conduct a Monte Carlo experimental study that compares and evaluates the bias and variance performance of the different strategies. From the theoretical and the simulation studies, we analyze the effect of different factors, such as the forecast horizon and the time series length, on the bias and variance components, and on the different multistep-ahead strategies. Several lessons are learned, and recommendations are given concerning the advantages, disadvantages, and best conditions of use of each strategy.
45
Neural Networks and the Bias/Variance Dilemma
Stuart Geman, Elie Bienenstock, René Doursat · Neural Computation · 1992 · 3.6K citations
Christopher G. Atkeson, Andrew Moore, Stefan Schaal · Artificial Intelligence Review · 1997 · 1.7K citations
25 years of time series forecasting
Jan G. De Gooijer, Rob J. Hyndman · International Journal of Forecasting · 2006 · 1.6K citations