|
on Forecasting |
| By: | Richard H. Cohen (College of Business and Public Policy, University of Alaska Anchorage); Carl Bonham (Department of Economics and University of Hawaii Economic Research Organization, University of Hawaii at Manoa) |
| Abstract: | This paper contributes to the literature on the modeling of survey forecasts using learning variables. We use individual industry data on yen-dollar exchange rate predictions at the two week, three month, and six month horizons supplied by the Japan Center for International Finance. Compared to earlier studies, our focus is not on testing a single type of learning model, whether univariate or mixed, but on searching over many types of learning models to determine if any are congruent. In addition to including the standard expectational variables (adaptive, extrapolative, and regressive), we also include a set of interactive variables which allow for lagged dependence of one industry’s forecast on the others. Our search produces a remarkably small number of congruent specifications-even when we allow for 1) a flexible lag specification, 2) endogenous break points and 3) an expansion of the initial list of regressors to include lagged dependent variables and use a General-to-Specific modeling strategy. We conclude that, regardless of forecasters’ ability to produce rational forecasts, they are not only “different,” but different in ways that cannot be adequately represented by learning models. |
| Keywords: | Learning Models, Exchange Rate, Survey Forecasts |
| Date: | 2007–07–25 |
| URL: | http://d.repec.org/n?u=RePEc:hai:wpaper:200718&r=for |
| By: | Todd E. Clark; Michael W. McCracken |
| Abstract: | This paper examines the asymptotic and finite-sample properties of tests of equal forecast accuracy applied to direct, multi-step predictions from both non-nested and nested linear regression models. In contrast to earlier work -- including West (1996), Clark and McCracken (2001, 2005),and McCracken (2006) -- our asymptotics take account of the real-time, revised nature of the data. Monte Carlo simulations indicate that our asymptotic approximations yield reasonable size and power properties in most circumstances. The paper concludes with an examination of the real-time predictive content of various measures of economic activity for inflation. |
| Keywords: | Forecasting |
| Date: | 2007 |
| URL: | http://d.repec.org/n?u=RePEc:fip:fedkrw:rwp07-06&r=for |
| By: | Jonas Dovern |
| Abstract: | We use the concept of predictability as presented in Diebold and Kilian (2001) to assess how well the growth rates of various components of German GDP can be forecasted. In particular, it is analyzed how well different commonly used leading indicators can increase predictability of these time series. To this end, we propose an algorithm to select an optimal information set from a full set of possible leading indicators. In the univariate set up, we find very small degrees of predictability for all quarterly growth rates whereas yearly growth rates seem to be more predictable at short forecast horizons. According to the algorithm proposed, from a set of financial leading indicators the short term interest rate is included in the highest number of information sets and from a set of survey indicators the ifo-business expectation index is included in most cases. Conditioning on the optimal sets of leading indicators improves the predictability of most of the quarterly growth rates substantially while the predictabilities of the yearly growth rates cannot be increased significantly further. The results indicate that there is clearly evidence that complicated forecasting models are usually superior to simple AR univariate models. |
| Keywords: | Predictability, Leading Indicators, GDP component |
| JEL: | C53 E37 |
| Date: | 2006–07 |
| URL: | http://d.repec.org/n?u=RePEc:kie:kieasw:436&r=for |