Optimal Provisional Estimation in Short-term Surveys

Timeliness is a driving feature of official statistics. In particular, in the short-term statistics framework usually a first provisional release is carried out on the basis of preliminary early respondents, followed by a final release based on late respondents as well. The revision is the difference (absolute or percent) between final and provisional estimates. In this context, according to a model assisted approach, we propose and compare some early estimation techniques aimed at reducing the average revision. Their properties are evaluated from a theoretical point of view and on the basis of an empirical attempt concerning the quarterly wholesale trade survey carried out by ISTAT (Italian National Statistical Institute) for the period 2003-2006, aimed at estimating changes along time of the quarterly average turnover.