Subsampling for Preliminary Estimates (Method)


Among the main components of the quality in official statistics, the timeliness seems to be one of the most relevant both for producers and users of statistical data. In particular timeliness is becoming a pressing target especially for short term statistics (EUROSTAT, 2000). Therefore, in recent years, in many fields of official short term statistics the timeliness is becoming the driving issue, both for the increasing demand of users and the need to fill the gap comparing to data release standards already achieved by USA and other developed countries. The Amendment EU Regulation on Short Term Statistics (introduced in August 2005, EUROSTAT) requests all the statistical institutes of the EU Member States to transmit preliminary short term indicators to EUROSTAT with a reduced delay comparing to the timeliness set in the original 1998 Regulation. Frequently, in the NSIs short term statistics are based on fixed panel surveys of enterprises or rotating panels with a partial overlap from one year to another. Auxiliary variables coming from the previous survey occasions are often available.

A common approach for dealing with preliminary estimates focuses essentially on the study and the definition of efficient estimators, exploiting almost exclusively auxiliary information in the estimation phase. In such context sampling has a marginal role. Preliminary estimation merely involves the use of the quick respondent units. In fact, in order to obtain “good” preliminary estimates, standard survey strategy often aims to achieve high quick response rate by means of a well-structured plan of follow up. In some surveys the “largest” units are carefully supervised. Following this approach, we point out that there is no explicit definition of sampling design for preliminary estimation, but that for the approach trying to observe large units. Hence, the preliminary estimates are usually drawn by a nonprobabilistic sample design. A useful documentation on preliminary estimation problems (even though not comprehensive) can be downloaded from the OECD web site.

The topic investigates alternative sampling approaches for planning the subsamples for preliminary estimates. These designs try to exploit the auxiliary information in an efficient way according to the estimator used for the preliminary and final estimation. Therefore, an overall strategy for the production of preliminary estimates is developed, involving both the sample design and the estimator definition.


To read the entire document, please access the pdf file (link under "Related Documents" on the right-hand-side of this page).


Your feedback is appreciated. Please send your remarks, suggestions for improvement, etc. to memobust@cbs.nl.