Understanding Statistics in the Age of Big Data

Kim Moldofsky is the publisher of The Maker Mom and STEM Kids Chicago.

Bombarded by images of shamrocks, Trifolium repens, on St. Patrick’s Day, I found myself pondering four-leaf clovers. Given that the white (Tri-folium) clover I typically find in fields and on my lawn is so-named because of its three leaves, the variety with four leaves presents a rare (lucky?) mutation. Only one in roughly 10,000 white clovers will develop a fourth leaf. As I pondered whether I’d spot a four-leaf clover this summer, my mind wandered to the topics of probability and statistics.

Living in a world that provides us with an increasing amount of feedback in the form of data, it’s important that students understand how this data can be used to paint an accurate picture of our world. Conversely, it’s crucial for them to understand how data can be abused and misleading.

To that end, I want to share a couple of resources that can be used to teach statistical literacy. These sites provide young scientists and their teachers tools to help them focus on the facts. And they’ll help you set the tone for Mathematics and Statistics Month, which in just around the corner in April.

Sites that Build Statistical Literacy

Check out what’s cooking at the STEW, the Statisics Education Web. This project of the American Statistical Association (ASA) provides peer-reviewed, standards-aligned lesson plans for students in grades K-12. Downloadable lesson plans include titles that will grab student interest, such as:

  • NFL Salaries

  • Who Sends the Most Text Messages

  • How Random is the iPod’s Shuffle Feature?

The United States Census Bureau offers lesson plans that tie in census data in bite-size, easy-to-use chunks to help students understand their school, community, and world. The site offers a range of topics to explore, including:

  • comparing classroom activities to national norms

  • quantifying a decade of immigration trends

  • comparing your home state to another state.

They also have ready-to-go lessons that help students understand what it means to post a statistical question and how to work with data sets.

The site provides some interesting data visualizations, too. If your students are intrigued, they may want to look through the Census site’s other data tools and apps. Maybe they’ll find something that will add new depth to their Young Scientist Challenge entry.

Correlation is not causation

One of the most common abuses of data comes from implying that correlation is the same as causation. Just because a relationship (correlation) between two events exists does not mean that one of those things caused the other one happen. Ask your students to get creative and come up with some examples. The site, Spurious Correlations provides fodder for inspiration. http://tylervigen.com/spurious-correlations

For example, did you know that there’s a strong positive correlation between the divorce rate in Maine and the per capita consumption of margarine?  

Understanding statistics data is an important life skill in the age of Big Data. Make sure your students have the finesse to explore and understand statistics with a critical eye.