摘要:

AbstractThis paper presents a comparative analysis of the sources of error in forecasts for the UK economy published over a recent four‐year period by four independent groups. This analysis rests on the archiving at the ESRC Macroeconomic Modelling Bureau of the original forecasts together with all their accompanying assumptions and adjustments. Amethod ofdecomposing observed forecast errors so as to distinguish the contributions of forecaster and model is set out; the impact of future expectations treated in a ‘model‐consistent’ or ‘rational’ manner is specifically considered. The results show that the forecaster's adjustments make a substantial contribution to forecast performance, a good part of which comes from adjustments that bring the model on track at the start of the forecast period. The publishedex‐anteforecasts are usually superior to pure model‐basedex‐postforecasts, whose performance indicates some misspecification of the

ISSN:0277-6693    

DOI:10.1002/for.3980100302

出版商:John Wiley&Sons, Ltd.    

年代:1991

数据来源: WILEY

摘要:

AbstractForecasts from quarterly econometric models are typically revised on a monthly basis to reflect the information in current economic data. The revision process usually involves setting targets for the quarterly values of endogenous variables for which monthly observations are available and then altering the intercept terms in the quarterly forecasting model to achieve the target values. A formal statistical approach to the use of monthly data to update quarterly forecasts is described and the procedure is applied to the Michigan Quarterly Econometric Model of the US Economy. The procedure is evaluated in terms of bothex postandex anteforecasting performance. Theex anteresults for 1986 and 1987 indicate that the method is quite promising. With a few notable exceptions, the formal procedure produces forecasts of GNP growth that are very close to the publishedex anteforecasts.

ISSN:0277-6693    

DOI:10.1002/for.3980100303

出版商:John Wiley&Sons, Ltd.    

年代:1991

数据来源: WILEY

摘要:

AbstractThis paper constructs current trend growth rates for a variety of U.K. monetary aggregates. These rates are computed from decompositions of intervention‐augmented ARIMA models, the interventions being identified and their magnitude estimated by an iterative detection procedur

ISSN:0277-6693    

DOI:10.1002/for.3980100304

出版商:John Wiley&Sons, Ltd.    

年代:1991

数据来源: WILEY

摘要:

AbstractDaily electricity consumption data, available almost in real time, can be used in Italy to estimate the level of industrial production in any given month before the month is over. We present a number of procedures that do this using electricity consumption in the first 14 days of the month. (This is an extension of a previous model that used monthly electricity data.) We show that, with a number of adjustments, a model using half‐monthly electricity data generates acceptable estimates of the monthly production index. More precisely, these estimates are more accurate than univariate forecasts but less accurate than estimates based on monthly electricity data. A further improvement can be obtained by combining ‘half‐monthly’ electricity‐based estimates with univariate forecasts. We also present quarterly estimates and discuss confidence intervals for various types of

ISSN:0277-6693    

DOI:10.1002/for.3980100305

出版商:John Wiley&Sons, Ltd.    

年代:1991

数据来源: WILEY

摘要:

AbstractThe three basic modelling approaches used to explain forest fire behaviour are theoretically, laboratory or empirically based. Results of all three approaches are reviewed, but it is noted that only the laboratory‐ and empirically based models have led to forecasting techniques that are in widespread use. These are the Rothermel model and the McArthur meters, respectively. Field tests designed to test the performance of these operational models were carried out in tropical grasslands. A preliminary analysis indicated that the Rothermel model overpredicted spread rates while the McArthur model underpredicted. To improve the forecast of bushfire rate of spread available to operational firefighting crews it is suggested that a time‐variable parameter (TYP) recursive least squares algorithm can be used to assign weights to the respective models, with the weights recursively updated as information on fire‐front location becomes available. Results of this methodology when applied to US Grasslands fire experiment data indicate that the quality of the input combined witha prioriknowledge of the performance of the candidate models plays an important role in the performance of the TVP algorithm. With high‐quality input data, the Rothermel model on its own outperformed the TVP algorithm, but with slightly inferior data both approaches were comparable. Though the use of all available data in a multiple linear regression produces a lower sum of squared errors than the recursive, time‐variable weighting approach, or that of any single model, the uncertainties of data input and consequent changes in weighting coefficients during operational conditions suggest the use of the TVP algorithm

ISSN:0277-6693    

DOI:10.1002/for.3980100306

出版商:John Wiley&Sons, Ltd.    

年代:1991

数据来源: WILEY

摘要:

AbstractThe paper presents an identification procedure for a dynamic model of am hydrologic process. The process involves solute transport in streams subject to aquifer interaction and unsteady flows and the intended use of the model is prediction. Detailed assumptions and results are provided to illustrate the level of comprehensive analysis required to assess model adequacy. The assessment procedure easily generalizes to any dynamic model which is linear‐in‐the‐parameters. As a fundamental tool, instrumental variable algorithms can be adopted which have a number of attractive features. These algorithms make both model‐order identification and specification among alternatives a straightforward task. They are known to be consistent estimators in the presence of a wide class of errors. It is seen that they can be made stable and robust in the presence of data outliers. Instrumental variable algorithms can also be used which are asymptotically efficient and provide a covariance matrix of parameter estimates. The paper shows how they aid the quantification of predictive uncertainty and investigates the validity of the underlying assumptions. Further, it illustrates that, when instrumental variable algorithms are used in recursive mode, they can be used not only as an additional tool to access model inadequacy but also as an aid to model impro

ISSN:0277-6693    

DOI:10.1002/for.3980100307

出版商:John Wiley&Sons, Ltd.    

年代:1991

数据来源: WILEY

ISSN:0277-6693    

DOI:10.1002/for.3980100301

出版商:John Wiley&Sons, Ltd.    

年代:1991

数据来源: WILEY