The Practice of Econometrics pp 131-148 | Cite as
Forecasting the daily balance of the Dutch Giro
Abstract
This paper is based on a consultancy project for the Dutch Postal Clearing Service, the ‘Giro’. The Giro plays an important part in transactions in the Netherlands. Specifically salary payments to households are important. As most of these take place on rather fixed days each month, and also have yearly patterns, the balance of the giro shows strong calendar variations and seasonality. Apart from that there are clearly trend movements. To develop a model to forecast all these movements was the goal of the project. This succeeded but the resulting model appeared much more complex than expected. Instead of the balance several flows of money going into and out of the system were modelled. Moreover each flow was decomposed into monthly aggregates showing trends and seasonality and the distribution of the aggregates over the days in each month showing all kinds of calendar effects. For all the submodels several possibilities have been tried, evolving from ad hoc solutions based on traditional time-series models to solutions based on the Kalman-filter. Around 1983 we discovered the latter possibilities, mainly due to the work of Harvey (1981). The Kalman-filter has a great appeal as a unified framework. Moreover the certainty that the specified models are optimally estimated — often not possible with ad hoc solutions — is reassuring.
Keywords
Kalman Filter Forecast Error Calendar Effect Seasonal Adjustment Trend MovementPreview
Unable to display preview. Download preview PDF.
Bibliography
- Bell WR and Hillmer SC. 1983. Modelling time series with calendar variation. Journal of the American Statistical Association, 78: 526–534.CrossRefGoogle Scholar
- Chow GC. 1983. Econometrics. New York: Mc.Graw-Hill.Google Scholar
- Cramer JS. 1969. Empirical Econometrics. Amsterdam: North-Holland Publishing Co.Google Scholar
- Gersch W and Kitagawa G. 1983. The prediction of time series with trends and seasonalities. Journal of Business & Economic Statistics, 1, 253–264.CrossRefGoogle Scholar
- Harrison PJ and Stevens CF. 1976. A Bayesian approach to short term forecasting. Journal of the Royal Statistical Society Series B, 38: 1325–1333.Google Scholar
- Harvey AC. 1981. Time series models. Oxford: Philip Allan.Google Scholar
- Harvey AC and. Todd PHJ. 1983. Forecasting economic time series with structural and Box-Jenkins models: a case study. Journal of Business & Economic Statistics, 1: 299–315.Google Scholar
- Harvey AC. 1984. A unified view of statistical forecasting procedures. Journal of Forecasting, 3: 245–275.CrossRefGoogle Scholar
- Learner EE. 1983. Model choice and specification analysis, ch. 5 of Handbook of Econometrics, 1. Amsterdam: North-Holland Publishing Co.Google Scholar
- Pfefferman D and Fisher JM. 1984. Festival and working days prior adjustment in economic time series. International Statistical Review, 50: 113–124.Google Scholar
- Pierce DA, Grape MR and Cleveland WP. 1984. Seasonal adjustment of the weekly monetary aggregates: a model-based approach. Journal of Business & Economic Statistics, 2: 260–270.CrossRefGoogle Scholar
- Vos AF de. 1975, 1984. Seasonal adjustment of unemployment figures; criteria and models. Dissertation University of Amsterdam (1975, Dutch) and unpublished paper (1976, Free University, Amsterdam ).Google Scholar
- Vos AFde. 1980. Univariate time-series analysis, lecture notes. Amsterdam: Interfaculteit Econometrie, Free University.Google Scholar
- Vos AF de. 1983. The specification of relations between time series, specifically money, income and interest (Dutch). Kwantitatieve Methoden, 10: 10–32.Google Scholar
- Young AH. 1968. Linear approximations to the Census and BLS seasonal adjustment methods. Journal of the American Statistical Association, 63: 445–471.CrossRefGoogle Scholar