This week I’m planning to identify some sources of data for you to use during your teaching of statistics, data literacy, etc. I’m convinced that using real data, whether collected in a survey by our students or downloaded from sources easily found on the web, engage students in ways in which many textbook problems do not. Too often I see problems which only use whole number data, for which the computed mean is also a whole number, and the calculated statistic doesn’t provide useful information. For example, what’s the point of finding the mean of 5 numbers? The mean represents the ‘middle’ of the data and, in a sense, represents all the data. With only 5 numbers, we can ‘see’ the middle without calculation.
I urge you to only use numbers with units. Finding the 5-number summary (box & whisker chart) of 25 numbers is much more interesting when those 25 numbers are the heights of your students, and you can ask, “What does the IQR of 32 inches tell us about the students in this class?”
One of my favorite quotes (from Ronald Coase), “If you torture the data long enough, it will confess.” reminds me that statistics, data analysis, etc. was created to reveal the story ‘hidden’ in the data; it was not created to produce a bunch of numbers (or to torture students). So, look for a ‘good’ story which will engage students.
I’ve listed some of my ‘favorite’ data resource websites below. Some have special sections for teachers/educators which include lesson plans and/or other helpful teaching/instructional supports including the data and the ‘story’ too.
One of my students’ favorites are the classroom ready data resources at:
There are many exciting topics in this website and, for those of you in my geographic area, one of them is Teaching Great Lakes Science. One of the features teachers appreciate is the data has been modified slightly to make it more accessible to young students (i.e. fewer decimal digits, spreadsheet format, etc.).
A more general recommendation is:
A Little Stats (http://alittlestats.blogspot.com/) is a blog from Amy Hogan. Click the Data Sources link and you’ll find a useful list of organized and annotated links. Another set of useful links this wonderful blog maintains is Stats Things Loved. Most of Data Sources are appropriate for use by school students, though I urge you to ‘monitor’ the data sources carefully – some may be inappropriate for your student population. Some of my students’ favorites in her list are:
https://www.nutritionix.com/database (which contains a huge grocery database), a whole set of links to sports data (e.g. https://www.nfl.com/stats/player-stats/, https://legacy.baseballprospectus.com/sortable/, and https://www.mlssoccer.com/stats), and https://www.encyclopedia-titanica.org/ (data about the Titanic which sunk in 1912).
Also, I recommend the Journal of Statistics Education website (http://jse.amstat.org/jse_data_archive.htm) which has a link to a set of datasets and accompanying stories. This website assists you by allowing teachers/students to access data with stories which can engage students, though many of the data sets are not current.
Another useful site is DASL (https://dasl.datadescription.com//). DASL provides data from a wide variety of topics so that statistics teachers can find interesting, real-world examples for their students. We know a good example can make a lesson on a particular statistics method vivid and relevant. This website is designed to help teachers locate and identify datafiles for teaching as well as serve as an archive for datasets from statistics literature.
Finally, I’d be remiss if I didn’t mention the United States Census Bureau website for teachers/students (https://www.census.gov/programs-surveys/sis/about/teachers-guide.html ) which includes a Teacher’s Guide to Data Access Tools for Students at: https://www.census.gov/programs-surveys/sis/about/teachers-guide.html
In particular, and as an example of the support for teachers, there are two strands. The first is:
aimed primarily at 8 – 12 year old students, and
for secondary students. These two strands have data and other useful information that will appeal to students at these age levels. Take a look.
Do you use any of these in your classroom? Would you use these as sources of data for teaching mathematics/statistics/data analysis?
Would you like more posts like this – reviews of 3-4 math websites, or something else? Tell us what would be most helpful right now or for the term following summer ‘break’?
Subscribe to the blog and never miss a post! If you like a blog, tell your friends and colleagues.
Have a question for the authors? Email us at congruentthoughts@nl.edu or tweet me at @GeorgeLitman1
Congruent Thoughts with Aleks & George 