Most psychology students will be introduced to the concept of Type 1 and Type 2 errors in a statistics class.
The aim of this post is to explore a couple of quick ways in which psychology instructors can make sure their students don't confuse Type 1 and Type 2 errors, and in doing so extend their understanding of null hypothesis significance testing.
One very simple way of illustrating the difference between Type 1 and Type 2 errors is to get students to think about erroneous test results.
From "Essential Guide to Effect Sizes" by Paul D. Ellis (2010).
Another great way is to provide a 'real world' perspective. Larry Gonick does an excellent job of doing this in his book - The Cartoon Guide to Statistics -, in which he suggests that we think of hypothesis testing/significance tests in terms of a smoke detector in our home. Gonick notes that household smoke-detectors tend to go off every time "you make the toast too dark" and this is a Type 1 error (an alarm without a fire) as opposed to a Type 2 error (a fire without an alarm). Adding that:
“Every cook knows how to avoid a Type 1 error: Just remove the batteries. Unfortunately, this increases the incidence of Type 2 errors!”
Outline Gonick's smoke alarm example and then get your students to come up with their own real world illustration of the difference between Type 1 and Type 2 errors. This task works best when students are divided into small groups. Not only does this allow students to bounce ideas off each other but it also means you can get each group to present their example to the rest of the class. You might also want to get the class as a whole to decide which is the best example and why.
If you to wish broaden out this activity, you may find the following questions/tasks useful.