Tyler Vigen has has created  a long list of easy-to-paste-into-a-powerpoint graphs that illustrate that correlation does not equal causation. For instance, while per capita consumption of cheese and number of people who die by become tangled in their bed sheets may have a strong relationship (r = 0.947091), no one is saying that cheese consumption leads to bed sheet-related death. Although, you could pose The Third Variable question to your students for some of these relationships). Property of Tyler Vigens, http://i.imgur.com/OfQYQW8.png Vigen has also provided a menu of frequently used variables (deaths by tripping, sunlight by state) to help you look for specific examples. This portion is interactive, as you and your students can generate your own graphs. Below, I generated a graph of marriage rates in Pennsylvania and consumption of high fructose corn syrup. Generated at http://www.tylervigen.com/

The Colbert Report's take on Kyle Copland's research studying whether or not gun ownership lowers crimes. Copland's method? Handing out free .22s in high crime areas (to folks that pass a background check and take a gun safety course). from ColbertNation.com This applies more to a research methods class (Colbert expresses a need for a control group in Copland's research. His suggestion? Sugar guns as well as a second experimental condition in which EVERYONE is given a gun). However, I imagine that you could show your students this video and pause it before they introduce the research project and ask your students how we could finally answer this question of whether or not gun ownership lowers crimes. Thanks to Chelsea for pointing this out!

So. I shared my little blog on the Teaching of Psychology list serv last week. And within the next 24 hours, I received about 1000 page views, which blew my mind. Honestly, I know it can be an up-hill battle to teach statistics and I love the idea that maybe I'm giving my colleagues some new ideas to spice up their classes. Better yet, I received emails from fellow psychologists with websites to share. One of these psychologists was Dr. Richard Landers from Old Dominion University. So, is it just me, or has anyone else thought, "Gosh, I wish I could just create a data set for <insert statistical test here> that would be <sig/ns> so that I could ensure that my students had the experience of analyzing that kind of test?" Well, Richard's website will provide you with exactly that!  Not only do you get the data set, but you get the APA write up and output for the data as well! Richard created it as a study guide for his students but I can see where...