|
on Forecasting |
| By: | George Athanasopoulos; Ashton de Silva |
| Abstract: | In this paper we propose a new set of multivariate stochastic models that capture time varying seasonality within the vector innovations structural time series (VISTS) framework. These models encapsulate exponential smoothing methods in a multivariate setting. The models considered are the local level, local trend and damped trend VISTS models with an additive multivariate seasonal component. We evaluate their performances for forecasting international tourist arrivals from eleven source countries to Australia and New Zealand. |
| Keywords: | Holt-Winters’ method, Stochastic seasonality, Vector innovations state space models. |
| JEL: | C32 C53 |
| Date: | 2010–02–22 |
| URL: | http://d.repec.org/n?u=RePEc:msh:ebswps:2009-11&r=for |
| By: | Exterkate, P.; Dijk, D.J.C. van; Heij, C.; Groenen, P.J.F. (Erasmus Econometric Institute) |
| Abstract: | Various ways of extracting macroeconomic information from a data-rich environment are compared with the objective of forecasting yield curves using the Nelson-Siegel model. Five issues in factor extraction are addressed, namely, selection of a subset of the available information, incorporation of the forecast objective in constructing factors, specification of a multivariate forecast objective, data grouping before constructing factors, and selection of the number of factors in a data-driven way. Our empirical results show that each of these features helps to improve forecast accuracy, especially for the shortest and longest maturities. The data-driven methods perform well in relatively volatile periods, when simpler models do not suffice. |
| Keywords: | yield curve prediction;Nelson-Siegel model;factor extraction;variable selection |
| Date: | 2010–02–23 |
| URL: | http://d.repec.org/n?u=RePEc:dgr:eureir:1765018254&r=for |
| By: | Jan J. J. Groen; Paolo A. Pesenti |
| Abstract: | In this paper we seek to produce forecasts of commodity price movements that can systematically improve on naive statistical benchmarks, and revisit the forecasting performance of changes in commodity currencies as efficient predictors of commodity prices, a view emphasized in the recent literature. In addition, we consider different types of factor-augmented models that use information from a large data set containing a variety of indicators of supply and demand conditions across major developed and developing countries. These factor-augmented models use either standard principal components or partial least squares (PLS) regression to extract dynamic factors from the data set. Our forecasting analysis considers ten alternative indices and sub-indices of spot prices for three different commodity classes across different periods. We find that the exchange rate-based model and especially the PLS factor-augmented model are more prone to outperform the naive statistical benchmarks. However, across our range of commodity price indices we are not able to generate out-of-sample forecasts that, on average, are systematically more accurate than predictions based on a random walk or autoregressive specifications. |
| JEL: | C23 C53 F47 |
| Date: | 2010–02 |
| URL: | http://d.repec.org/n?u=RePEc:nbr:nberwo:15743&r=for |
| By: | Ehrmann, M.; Eijffinger, S.C.W. (Tilburg University); Fratzcher, M. |
| Date: | 2010 |
| URL: | http://d.repec.org/n?u=RePEc:ner:tilbur:urn:nbn:nl:ui:12-3763052&r=for |
| By: | Proietti, Tommaso |
| Abstract: | Seasonality is one of the most important features of economic time series. The possibility to abstract from seasonality for the assessment of economic conditions is a widely debated issue. In this paper we propose a strategy for assessing the role of seasonal adjustment on business cycle measurement. In particular, we provide a method for quantifying the contribution to the unreliability of the estimated cycles extracted by popular filters, such as Baxter and King and Hodrick-Prescott. The main conclusion is that the contribution is larger around the turning points of the series and at the extremes of the sample period; moreover, it much more sizeable for highpass filters, like the Hodrick-Prescott filter, which retain to a great extent the high frequency fluctuations in a time series, the latter being the ones that are more affected by seasonal adjustment. If a bandpass component is considered, the effect has reduced size. Finally, we discuss the role of forecast extensions and the prediction of the cycle. For the time series of industrial production considered in the illustration, it is not possible to provide a reliable estimate of the cycle at the end of the sample. |
| Keywords: | Linear filters; Unobserved Components; Seasonal Adjustment; Reliability. |
| JEL: | E32 C22 |
| Date: | 2010–02–21 |
| URL: | http://d.repec.org/n?u=RePEc:pra:mprapa:20868&r=for |
| By: | Jaarsveld, W.L. van (Erasmus Econometric Institute) |
| Abstract: | In this paper obsolescence of service parts is analyzed in a practical environment. Based on the analysis, we propose a method that can be used to estimate the risk of obsolescence of service parts. The method distinguishes groups of service parts. For these groups, the risk of obsolescence is estimated using the behavior of similar groups of service parts in the past. The method uses demand data as main information source, and can therefore be applied without the use of an expert's opinion. We will give numerical values for the risk of obsolescence obtained with the method, and the e®ects of these values on inventory control will be examined. |
| Keywords: | inventory;spare parts;obsolescence;forecasting |
| Date: | 2010–02–17 |
| URL: | http://d.repec.org/n?u=RePEc:dgr:eureir:1765018045&r=for |
| By: | Byung-Kwang Yoo; Megumi Kasajima; Jay Bhattacharya |
| Abstract: | In June 2009, the World Health Organization declared that novel influenza A (nH1N1) had reached pandemic status worldwide. The response to the spread of this virus by the public and by the public health community was immediate and widespread. Among the responses included voluntary avoidance of public spaces, closure of schools, the ubiquitous placement of hand sanitizer, and the use of face masks in public places. Existing forecasting models of the epidemic spread of nH1N1, used by public health officials to aid in making many decisions including vaccination policy, ignore avoidance responses in the formal modeling. In this paper, we build a forecasting model of the nH1N1 epidemic that explicitly accounts for avoidance behavior. We use data from the U.S. summer and the Australian winter nH1N1 epidemic of 2009 to estimate the parameters of our model and forecast the course of the epidemic in the U.S. in 2010. We find that accounting for avoidance responses results in a better fitting forecasting model. We also find that in models with avoidance, the marginal return in terms of saved lives and reduced infection rates of an early vaccination campaign are higher. |
| JEL: | I1 I10 |
| Date: | 2010–02 |
| URL: | http://d.repec.org/n?u=RePEc:nbr:nberwo:15752&r=for |