1. Anna Bombak, Chuck Humphrey, Lindsay Johnston and Leah Vanderjagt University of Alberta The Winter Institute on Statistical Literacy for Librarians Demystifying statistics for the practitioner

2. Outline Introductions Statistics and data: what are we talking about? Definitions, standards and metadata Official statistics: national Official statistics: international Census geography and small area statistics Non-official statistics

3. Summary When looking for statistics, think about a likely data source from which they would be produced and the likely agency that would produce such statistics. Use the official and non-official classification to help identify producers of statistics. The path toward official statistics takes you to governmental sources. The path toward non-official statistics takes you to commercial and non-governmental organizations.

4. Non-official statistical sources Marketing and consumer research Academic research Private research institutes Professional associations & unions Trade organizations Special interest groups Commercial statistics vendors Non-governmental organizations

5. An example: political corruption A patron wanted to know the level of political corruption for the countries of the world.  Who would produce such a statistic?  What possible data source would exist? From the perspective of international investors, this is a useful statistic. The Political Risk Yearbook A pathfinder at Princeton on Economic and Political Riskpathfinder

6. Business statistical sources Economic Statistics  Provincial/National/International Industries Companies  Publicly traded  Private Commodities  Prices Prices  Trade Trade Consumers  Marketing Marketing

7. Consumer patterns Exercise 7 makes use of two non-official consumer surveys to support marketing research. You will be asked to find the number of households with cats or using products for cats nationally and internationally.

8. Formats for statistical information You have seen over the past two and a half days a variety of formats used to disseminate statistical information, including HTML, CSV, IVT and XLS.variety of formats Which one should you use?  Your patron’s context should come first. How does she/he intend to use the statistics? Does she/he have software to use the format?  Proprietary versus open format.  Avoid display formats (eg., HTML) over content delivery formats (eg., CSV)

9. Citations for statistics Gaetan Drolet, a retired data librarian from the University of Laval, worked part-time for DLI compiling a citation guide for Statistics Canada. This has been officially adopted within Statistics Canada and has its own catalogue number: 12-591-XWE12-591-XWE Examples:  Source: Statistics Canada, Survey of Financial Security (SFS). Source:  Census, 2006 Census, 2006  E-STAT E-STAT

10. Summary of strategies Gov publications approach  What agency would produce such a statistic? Does the mandate or goals include the scope of content? Who are the members of the agency, if the agency is a membership organization?  What jurisdiction responsible for this content?  Is this likely an official or non-official statistic?  What publication titles are related to this content?  What is the availability of statistics from the agency Data librarian approach  What data source would be used to produce such a statistic?  Who would collect such data?  What unit of observation would be needed to produce such a statistics?  What would the structure of the table look like given time, geography and attributes of the unit of observation?  Would the source be in the realm of official or non-official statistics?  Use the literature trail and its indexes (non-official vs. official publications)

11. Chart of numeric information

12. Statistical confidence Confidence a mathematical concept and it’s an attitude. We have been more concerned the past three days with the latter than the former. Statisticians will deal with the confidence intervals associated with the release of statistics. You should now have confidence to help patrons find statistics.