Computer Science ApplicationsManagement Science and Operations ResearchEconomics and EconometricsModeling and SimulationStatistics, Probability and UncertaintyStrategy and Management
AbstractIt is well known that a linear combination of forecasts can outperform individual forecasts. The common practice, however, is to obtain a weighted average of forecasts, with the weights adding up to unity. This paper considers three alternative approaches to obtaining linear combinations. It is shown that the best method is to add a constant term and not to constrain the weights to add to unity. These methods are tested with data on forecasts of quarterly hog prices, both within and out of sample. It is demonstrated that the optimum method proposed here is superior to the common practice of letting the weights add up to one.
AbstractA univariate structural time series model based on the traditional decomposition into trend, seasonal and irregular components is defined. A number of methods of computing maximum likelihood estimators are then considered. These include direct maximization of various time domain likelihood function. The asymptotic properties of the estimators are given and a comparison between the various methods in terms of computational efficiency and accuracy is made. The methods are then extended to models with explanatory variables.
AbstractA storm surge barrier was constructed in 1987 in the Oosterschelde estuary in the south‐western delta of Holland to provide protection from flooding, while largely maintaining the tidal characteristics of the estuary. Despite efforts to minimize the hydraulic changes resulting from the barrage, it was expected that exchange with the North Sea, suspended sediment concentration and nutrient loads would decrease considerably. A model of the nutrients, algae and bottom organisms (mainly cockles and mussels) was developed to predict possible changes in the availability of food for these organisms. Although the model is based on standard constructs of ecology and hydraulics, many of its parameters are known with but low accuracy, being expressed as a range of possible values only. Running the model with all possible values of the parameters gives rise to a fairly wide range of model output responses. The calibration procedure used herein does not seek a single optimal value for the parameters but a decrease in the parameter range and thus a reduction in model prediction uncertainty. The field data available for calibration of the model are weighted according to their relationship with the model's objective, i.e. to predict food availability for shellfish. Despite the considerable physical changes resulting from the barrier food availability for shellfish is predicted to remain largely unchanged, due to the compensating effects of several other accompanying changes. There appears to be room for the extension of mussel culture, but at an increased risk of adverse conditions arising.
AbstractThis paper investigates the time‐varying volatility patterns of some major commodities as well as the potential factors that drive their long‐term volatility component. For this purpose, we make use of a recently proposed generalized autoregressive conditional heteroskedasticity–mixed data sampling approach, which typically allows us to examine the role of economic and financial variables of different frequencies. Using commodity futures for Crude Oil (WTI and Brent), Gold, Silver and Platinum, as well as a commodity index, our results show the necessity for disentangling the short‐term and long‐term components in modeling and forecasting commodity volatility. They also indicate that the long‐term volatility of most commodity futures is significantly driven by the level of global real economic activity as well as changes in consumer sentiment, industrial production, and economic policy uncertainty. However, the forecasting results are not alike across commodity futures as no single model fits all commodities.