𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Preliminary data and econometric forecasting: an application with the Bank of Italy Quarterly Model

✍ Scribed by Fabio Busetti


Publisher
John Wiley and Sons
Year
2005
Tongue
English
Weight
240 KB
Volume
25
Category
Article
ISSN
0277-6693

No coin nor oath required. For personal study only.

✦ Synopsis


This paper discusses the use of preliminary data in econometric forecasting. The standard practice is to ignore the distinction between preliminary and final data, the forecasts that do so here being termed naïve forecasts. It is shown that in dynamic models a multistep-ahead naïve forecast can achieve a lower mean square error than a single-step-ahead one, as it is less affected by the measurement noise embedded in the preliminary observations. The minimum mean square error forecasts are obtained by optimally combining the information provided by the model and the new information contained in the preliminary data, which can be done within the state space framework as suggested in numerous papers. Here two simple, in general suboptimal, methods of combining the two sources of information are considered: modifying the forecast initial conditions by means of standard regressions and using intercept corrections. The issues are explored using Italian national accounts data and the Bank of Italy Quarterly Econometric Model.