论文信息 - Monitoring Schemes in Short-term Forecasting

Monitoring Schemes in Short-term Forecasting

A necessary ingredient of a practical short-term forecasting system in which the parameters of the demand model are not adaptive is some form of monitoring to detect changes in the demand pattern for which the model is inadequate. There are two major automatic methods currently in use for accomplishing this aim. The present paper compares the performances of these two schemes by the use of simulation and gives tables which may be used as a basis for the selection of a suitable scheme in a variety of situations.

E. R. Golder | J. G. Settle | J. Settle

[1] M. E. Muller,et al. A Note on the Generation of Random Normal Deviates , 1958 .

[2] G. Box,et al. Cumulative Sum Tests: Theory and Practice , 1968 .

[3] D. Y. Downham,et al. Multiplicative congruential pseudo-random number generators , 1967, Comput. J..

[4] A. F. Bissell,et al. Cusum Techniques for Quality Control , 1969 .

[5] E. R. Golder,et al. The Box‐Müller Method for Generating Pseudo‐Random Normal Deviates , 1976 .

[6] Henry R. Neave,et al. On Using the Box‐Müller Transformation with Multiplicative Congruential Pseudo‐Random Number Generators , 1973 .

[7] K. W. Kemp,et al. Sampling inspection of continuous processes with no autocorrelation between successive results , 1960 .

[8] O. L. Davies,et al. The Use of Cumulative Sum Cusum Techniques for the Control of Routine Forecasts of Product Demand , 1964 .

[9] Robert Goodell Brown,et al. Smoothing, forecasting and prediction of discrete time series , 1964 .

[10] R. H. Woodward,et al. Cumulative Sum Techniques , 1964 .

[11] W. D. Ewan. When and How to Use Cu-Sum Charts , 1963 .