This teaching example: 1. Is psychology research. 2. Features the actual data from the generous and helpful Dr. Bray . 3. Features GIFs. EVERYTHING is better with GIFs. 4. Includes puppies. 5. Includes a good ol' Psych Statistics standard: The one-sample t-test. Okay, get ready. I first learned about Dr. Emily Bray's dog cognition research via Twitter . Never let it be said that good things don't happen on Twitter. Occasionally.  1 Dogs are known for their ability to cooperate with humans and read our social cues. But are these skills biologically prepared? To find out, we tested 375 puppies at 8.5 weeks on 4 social cognition tasks (task descriptions: https://t.co/aETequNBce ) #AnimBehav2021 #Cognition pic.twitter.com/7vN2lp82Dp — Emily Bray (@DrEmilyBray) January 27, 2021 This is such a helpful way to share your research. This example works for your Cognitive or RM classes as well as your stats class, since this thread illustrates not just her findings but her methods. T...

When I teach inferential statistics, I think it is helpful in providing several conceptual (no by hand calculations, no data analyzed via computer) examples of experiments that could be analyzed using each inferential test. I also think it is essential to use non-psychology examples and psychology examples because students need to see how stats apply outside of psychology. At times, I believe that students are convinced that a class called Psychological Statistics doesn't apply outside of psychology.  So I like this quick, easy-to-follow example from medicine. Thomas, Patel, and Bittel (2021) studied how different vitamin supplements affected outcomes for people with COVID-19. The factor (COVID intervention) has four levels (usual care/control, ascorbic acid, zinc gluconate, and ascorbic acid/zinc gluconate). And the four groups acted pretty much the same. Bonus stats content: Error bars, super-cool Visual Summary of a research study that really highlights the most essential parts...

Stuart Ritchie wrote an excellent book about the problems (and solutions to those problems) in science called Science Fictions . Illustrator and author Zach Weinersmith summarized and illustrated those problems in science in the form of a short webcomic . Both the book and the comic are great and have a home somewhere in your psychology curriculum. The comic is a quick, digestible primer on the problems with science. Meanwhile, the book goes into great depth, including many of the problems related directly to p-hacking, fishing expeditions, etc.  For more, read Stuart's book, Science Fictions. Aside: I am American, and he is Scottish and reads the audiobook version to me while I walk my dog, and it is soothing. I'm creating a one-credit course for our Honors program based on this book.  Also, follow Stuart and Zach on The Bird App.

FlowingData shared some interesting info on how much cars cost version their environmental footprint .  TL;DR: Low emission cars tend to be cheaper in the long run. Hooray for the free market! The data is also available via the New York Times , along with a much more in-depth conversation about the actual cost of high/low emission cars, but it is behind a paywall. The original data, presented in a fun (nerd fun) interactive website , is available here.  How to use it in class: 1) It's a correlation! Each car model is a dot with two related data points: Average cost per month and average carbon dioxide emissions per mile.  2) It's Simpson's Paradox! Note how electric cars (yellow cloud all have similar emissions, but the average cost per month varies. Same for Diesel cars. Overall, you still see the positive correlation in the data, but if you break it down by class of car, the correlation isn't present for every level. 

I gave one of the keynote addresses at the STP Teaching Pre-conference this year. I'm so sad that we weren't all able to come together face to face, but I am so glad that I was invited to give this talk at a pre-conference I've attended off and on for years. Here is the PowerPoint. There are a bunch of links. TL;DR: You should do discussions in your stats classes. No, don't talk about degrees of freedom or bar graphs for an hour. Instead, help your novice statisticians see data (and your class!) IRL. A few details on my discussion days, and how it goes: I spend a full 55-minute period on the discussions. My students must submit a brief reflection piece about the readings. Here is how I describe the reflection piece and Discussion Day in my syllabus: Here is how I present the Discussion Day materials to my students:

If you are trying to explain the Chi-Square Test of Independence to your students, here are some timely examples that are political and not polarizing. Well, I don't think it is polarizing. I'm sure there are people out there that disagree. Maybe some of the questions are polarizing? Regardless, it is nice to have an example that uses a current event with easy to understand data.  The example comes from  CNN. The network conducted exit polling during the 2020 presidential election . I'm sure they didn't intend to provide us with a bunch of chi-square examples, but here we are. Essentially, CNN divided Biden and Trump voters into many categories with not a parameter to be had. I have included a few of the tables here, but there are many others on the website .  They illustrate different designs (2x2, 2x3, 2x4, etc.) and different magnitudes of difference between expected and observed values. 

Do you know what bugs me? How much time different intro stats textbooks spend talking about probability, lots of A not B stuff*, lots of probability associated with the normal distribution, etc. But we don't take advantage of the discussion to warn their students about the evils of relative vs. absolute risk. #statsliteracy Relative risk is the most clickbaity abuse of statistics that there is. Well, maybe the causal claims based on correlational data are more common. But I think the relative risk is used to straight-up scare people, possibly changing their behaviors and choices. I thought of it most recently when The Daily Mail (bless) used explained the difference in COVID-19 risk between dog owners and non-dog owners .   Here is the data described in the headline, straight from the original paper : Really, Daily Mail? How dare you. I think the most clever, trickiest, sneakiest ways to mislead with data are by not lying with data at all. Most truncated y-axes display actual ...