Sunday, September 4, 2011

Statistics User Quality Assurance Criteria

1. Source of data - who, source of original production or only publishing? Official statistics or not?
2. Intermediates - if so how many? If many intermediates there is probably a higher risk for different kind of faults and mistakes in terms of data and metadata.
3. Metadata - is there information about methods, definitions, classifications etc. easily available (linked to figures, tables, producers or publishers)?
4. Contact - is there a contact address to a person, institution by mail or telephone for handling queries?
5. Updating of tables - is there any indication the table/diagram will be updated over time? If so, probably better quality.
6. Benchmarking the website, e.g. The algorithm uses a proprietary blend of over 50 different variables, including search engine data, website structure, approximate traffic, site performance, and others.

No comments:

Post a Comment

Note: Only a member of this blog may post a comment.