Total Survey Error in Practice

17ASPIRE: An Approach for Evaluating and Reducing the Total Error in Statistical Products with Application to Registers and the National Accounts

Paul P. Biemer,^1,2 Dennis Trewin,³ Heather Bergdahl,⁴ and Yingfu Xie⁴

¹ Social, Statistical, and Environmental Sciences, RTI International, Research Triangle Park, NC, USA

² Odum Institute for Research in Social Science, University of North Carolina, Chapel Hill, NC, USA

³ Former Australian Statistician, Australian Bureau of Statistics, Canberra, Australia

⁴ Process Department, Statistics Sweden, Stockholm, Sweden

17.1 Introduction and Background

In 2011, following some difficulties with the consumer price index (CPI) and some incidents with other official statistics, the Swedish Ministry of Finance required that Statistics Sweden, Sweden’s National Statistical Office, develop a quality review and improvement system that relies on quality indicators and enables changes in quality over time to be assessed. It was the difficulties with the CPI that had the highest profile. There were numerous stories in the Swedish media, see Statistics Sweden (2009) for details.

The Ministry also required the highest priority areas for improvement to be identified. Further, they required that the process (i) be accessible to nonstatistical and nontechnical audiences and (ii) be as simple as possible while capturing all the critical components of data quality. Their main interest was data quality and the accuracy of official statistics published by ...