Score contribution per author:
α: calibrated so average coauthorship-adjusted count equals average raw count
There is an urgent policy need for regional (subnational) estimates for assessing regional policies and programmes. Often regional indicators, in particular those concerning poverty and social exclusion, have to be derived from surveys with sample size and design determined primarily to serve estimation at the national level. In the specific context of EU-SILC surveys and the Headline Indicator at-risk-of-poverty or social exclusion (AROPE) and its components defined by European Commission, this paper aims to contribute to the methodology for constructing such indicators at the regional level. The main difficulty arises from the smallness of regional samples in national surveys. The paper focuses on two related issues: identifying procedures potentially useful for improving sampling precision of regional estimates; and improving the precision of sampling error estimates of regional statistics based on small but complex samples. In addition to some results presented for a large number of OECD countries, more detailed numerical illustration is provided for two countries (Austria and Spain) based on EU-SILC data.