Assessing errors in data is crucial to producers of statistics and academic statisticians alike. Because information comprised of large quantities of data always contains errors, statisticians have been developing methods for assessing their effects. Standards have also been developed in official statistics for the assessing of statistical quality. At the ISI conference, Raoul Depoutot will give an account of Eurostat's quality standards and measurement processes
There are seven components of quality in statistics: relevance, accuracy, timeliness and regularity, clarity and accessibility, comparability, coherence and completeness. The components seen as the most important for European statistics are comparability, coherence and completeness.
In Europe, comparability of geographical data is a matter of particular importance and one needing a lot of development work. Coherence, for its part, aims for compatibility between statistics on different subject areas. Users' needs form the criteria for the completeness of a statistical system.
140 presentations on Wednesday
A total of 140 presentations will be made at the conference on Wednesday, on topics ranging between improving the quality and reliability of statistics, statistical issues in environmental and health and social service monitoring, measuring poverty, inequality and income distribution and educational statistics.
Further information about the conference programme:
Jussi Melkas, tel. +358 9 1734 3200;
Virpi Viertola, tel. +358 50 568 7444;
Kristiina Niklander, tel. +358 50 373 6510
Short English abstracts at: http://www.stat.fi/isi99/proceedings.html