Sometimes, I post whole class lessons. Sometimes, I post short little example nuggets. Today I share the latter.  This one is a brief, easy-to-understand example of why AI only learns what we teach it and how even a smarty pants computer can get a little confused about correlations and what they mean. A great way to introduce ML, AI, problems with both, and even discuss correlation and predictions and regression. https://twitter.com/hoalycu/status/1507770891786096643...in my head, I imagine that AI was just judging comic-sans font. The text in this tweet was from a MIT Technology Review article by WIll Douglas Heaven: https://www.technologyreview.com/2021/07/30/1030329/machine-learning-ai-failed-covid-hospital-diagnosis-pandemic/ If you want to go deeper with this example, I strongly recommend reading Dr. Cat Hicks's thread about this post:  https://twitter.com/grimalkina/status/1508095358693302275 .

A bit over a year ago, Susan Nolan asked me to chair the Statistical Literacy, Reasoning, and Thinking, Guidelines 2.0 for the Society for the Teaching of Psychology.  We were asked to explore and provide guidance for a) teaching statistical thinking in intro psychology and b) understanding how statistical thinking is taught across the psychology curriculum. This post will highlight the accomplishments of the first group, which created easy-to-implement teaching exercises that emphasize statistical reasoning skills in Intro Psych. The Guidelines 1.0 group provided lists of topics included in Intro Psych. The Guidelines 2.0 convened and created a series of brief, easy-to-apply exercises that correspond to the core topics typically taught in Intro. The sub-committee chair, Dr. Garth Neufeld, shared his considerable expertise about Intro Psychology to lead the group and center each exercise in American Psychological Association and American Statistical Association guidelines for under...

 Sophie Hill created a great game that shows students how to "eyeball" regression lines (or just lines) by guessing the y-intercept and the slope.  At the beginning of the game, you get a scatter plot. Then, you need to guess the y-intercept and the slope.   Once you make a guess, it will show you the actual line of best fit...and your line, along with residuals and mean squared error. So, this doesn't just allow for eyeballing the regression line but also how to test the fit of a line. P.S.: If you liked this, you'd love the Guess the Correlation game.