Skip to Main Content

Finding Data and Statistics Sources: Understanding Statistics

Overview

Locating statistics is easier if you understand the types of statistical information available.

Statistics are available on an enormous variety of topics. Examples: 

  • Batting averages for major league baseball players
  • Teen pregnancy rates in a particular city
  • Average income of residents of a particular State

Statistics are gathered/collected:

  • To demonstrate need or a use for information
  • For internal use within agencies and/or for use by the public. 

Available sources of statistics grow almost daily.

The Information in this guide was re-used and adapted with permission of Angela Bonnell of Illinois State University, Milner Library.

Understanding Statistics

It is helpful to know the factors that affect the creation of statistics:

  • An established need, interest, law, or reason must exist before resources will be invested in collecting, analyzing, and publishing the data.
  • Financial factors often drive the collection of statistical information. An organization may need information to help them make money, save money, or spend money in the best way possible.
  • It must be feasible to collect data on the topic. Some demographic groups or topics may prove difficult or impossible to collect data about.  Homeless people are more difficult to collect information about than homeowners, for instance.
  • Usually there is more information available at the national level than at state or local levels.  
  • Sometimes the exact information that you seek is not available, but by modifying your query or changing your topic slightly, the data can often be found. For example, you may not be able to find how many people in Illinois play golf each year, but you might be able to find how many people in the United States play golf each year.  

Sometimes you'll need assistance to find exactly what you need--please don't hesitate to ask a librarian for help if you are not finding what you want!

Statistics are compiled by many different types of agencies and organizations:

  • Federal, state, and local governments
  • Special interest groups
  • Think tanks and policy institutes
  • Private corporations
  • Professional organizations and associations
  • Educational institutions and independent researchers
  • Religious organizations
  • Political groups
  • Nonprofit organizations
  • Public interest groups
  • Media

In looking for statistical information, it is helpful to think about who would be interested in the information. For example, the number of elementary school children enrolled in private schools is likely to be of interest to government agencies concerned with education. In fact, this statistic can be found in the U.S. Department of Education publication Digest of Education Statistics. 

 

While statistics exist on a great number of topics, some statistical data may not be available. Many factors affect when and if data is available for a particular time period, topic, or population:

  • The fiscal or calendar year must end before annual statistics can be compiled.
  • Raw data (or data sets) must be compiled, analyzed, and put into usable form before being published.
  • Due to the lag time between collection, analysis, and publication, data is usually not available for the most current year.
  • Statistical information considered proprietary or confidential in nature may not be made available to external groups. For example, the average executive salary at a private company is rarely available.
  • A non-profit agency might collect demographic information for the clients they serve, but this information may not be released to the public due to confidentiality.
  • A corporation might have assembled marketing data on a target consumer group; however, they may consider it proprietary information and not make the statistics public to maintain a market advantage.
 
 

Statistical information can be divided into two types: data sets and compiled statistics.

While you will primarily be using compiled statistics, it is important to understand both formats of information.

 
  • Data in its purest form - sometimes referred to as "raw data"
  • Consist of information that has been collected but not yet analyzed in a meaningful way
  • Data that you will have to analyze yourself; a data sets has not yet been turned into usable information like summaries, charts, tables or graphics
  • Very large quantities of information
  • May require use of a codebook or manual to be understood

To use data sets effectively, it is important to be aware of:

  • who compiled the data,
  • the methodology used (how the data was collected), and
  • when the data was collected
  • Compressed forms of information or data. In other words, data that has been analyzed and turned into usable information.
  • Usually presented in charts, tables, maps or other graphics
  • The column and row headings of the charts and tables, as well as any written summary or footnotes, help to provide meaning and context for the information
  • Different units of measurement may be used to help convey the information in a usable form

To use compiled statistics effectively, it is important to be aware of:

  • who compiled the statistics,
  • what methodology was used (how the data was collected and analyzed), 
  • when the statistics were compiled and analyzed and, 
  • when the original data was collected.  Note: A statistic may be collected as part of a data set months or years before it is analyzed.  
Compiled statistics are generated from the analysis and/or visual representation of data sets.

Statistics eBooks

link to how to access e-books document