|
on Forecasting |
| By: | Ralph D. Snyder; Anne B. Koehler |
| Abstract: | It is a common practice to complement a forecasting method such as simple exponential smoothing with a monitoring scheme to detect those situations where forecasts have failed to adapt to structural change. It will be suggested in this paper that the equations for simple exponential smoothing can be augmented by a common monitoring statistic to provide a method that automatically adapts to structural change without human intervention. It is shown that the resulting equations conform to those of damped trend corrected exponential smoothing. In a similar manner, exponential smoothing with drift, when augmented by the same monitoring statistic, produces equations that split the trend into long term and short term components. |
| Keywords: | Forecasting, exponential smoothing, tracking signals. |
| JEL: | C32 |
| Date: | 2006–08 |
| URL: | http://d.repec.org/n?u=RePEc:msh:ebswps:2006-16&r=for |
| By: | C. Hamel; M. Herrmann; S. Lee; Keith Criddle; H. Geier |
| Abstract: | Forecasts of the regional economic impacts of changes in the demand for recreation occasioned by regulatory changes, changes in the quality of the recreation experience, or changes in average trip costs require a model that links changes in these trip attributes to individual participation decisions and population participation rates. The probability that an individual will take a particular recreational trip is described using a nonlinear random effects probit model based on variable trip attributes and individual economic and demographic characteristics. These conditional individual probabilities are transformed into predictions of changes in total recreation demand using a simulation-based sample enumeration method. The regional impacts associated with ensuing changes in primary and secondary expenditure patterns are elucidated with a stand-alone recreation-sector module linked to a regionally adjusted zip code-level input-output model. Because the participation model allows for nonconstant marginal utility, primary and secondary impacts exhibit nonlinear responses to variations in trip attributes. The modeling approach is demonstrated in an application to the saltwater sport fisheries for Pacific halibut and salmon in Lower and Central Cook Inlet, Alaska. |
| URL: | http://d.repec.org/n?u=RePEc:usu:wpaper:2001-01&r=for |
| By: | Miguel Herce; John E. Parsons; Robert C. Ready |
| Abstract: | Oil prices are very volatile. But much of this volatility seems to reflect short-term, transitory factors that may have little or no influence on the price in the long run. Many major investment decisions should be guided by a model of the long-term price of oil and its dynamics. Data on futures prices can be used to filter out the short-term volatility and recover a time series of the latent, long-term price of oil. We test a leading model known as the 2-factor or short-term, long-term model. While the generated latent price variable is clearly an improvement over the raw spot oil price series, we also find that (1) the generated long-term price series still contains some of the short-term volatility, and (2) a naïve use of a long-maturity futures price as a proxy for the long-term price successfully filters out a large majority of the short-term volatility and so may be convenient alternative to the more cumbersome model. |
| Date: | 2006–04 |
| URL: | http://d.repec.org/n?u=RePEc:mee:wpaper:0605&r=for |