I love InformationIsBeautiful . They created my favorite data visualization of all tim e.  They also created an interactive scatterplot with all sorts of information about Marvel Comic Universe  films. How to use in class: 1. Experiment with the outcome variables you can add to the X and Y axes: Critical response, budget, box office receipts, year of release, etc. There are more than that; you can add them to either the X or Y axes. So, it is one website, but there are many ways to assess the various films. 2. Because of interactive axes, there are various correlation and regression examples. And these visualizations aren't just available as a quick visual example of linear relationships...see item 3... 3. You can ask your students to conduct the actual data analyses you can visualize because  the hecking data is available . 4. The website offers exciting analyses, encouraging your students to think critically about what the data tells them. 5. You could also squeeze Simp...

This example is from The Economist and behind a paywall. However, it is worth using one of your free monthly views to see these visualizations of how much improvement Ps experience. That said, whenever I talk about antidepressants in class, I remind my students MANY TIMES that I'm not that kind of psychologist, and even if I was, I'm not their psychologist. Instead, they should direct any and all medication questions to their own psychologist. This blog post was inspired by " Antidepressants are over-prescribed, but genuinely help some patients " from The Economist, which was in turn inspired by  " Response to acute monotherapy for major depressive disorder in randomized, placebo-controlled trials submitted to the US FDA: individual participant data analysis", by M.B. Stone et al., BMJ, 2022; "Selective publication of antidepressant trials and its influence on apparent efficacy: updated comparisons and meta-analyses of newer versus older trial s", ...

When I teach regression, I touch on AI/Machine Learning. Because it is fancy regression and ties classroom lessons to real life. During discussions about AI/ML, we often talk about "training" computers to look for something by feeding computers data. Which is slightly abstract. And a bit boring, if you are just talking about a ton of spreadsheets. As an alternative to boring, I propose you ask your students to help train Google's computers to recognize doodles . Visit this website, and a prompt flashes on your screen: You draw the prompt (I used my touchscreen), and Google tries to guess what you drew. Here is my half-done wine glass. Google guessed what it was. The website includes additional information on the data that has already been collected. For every one of the doodles above, you can click through and look at all the ones created in response to each prompt. SO MUCH INFORMATION. If you would like, you can also show your students this explainer video.

 Many of my students love a good manicure.  Sometimes, they come in with full-on talons.  The youth love manicures.  As such, the recent viral headlines about gel nail polish lamps and cancer matter to them.  #scicomm But what did the original research really study? https://www.nature.com/articles/s41467-023-35876-8#Sec12 (CHECK OUT THIS GREAT RM IMAGE FROM THE ORIGINAL RESEARCH!!!) This  short NPR story by Rachel Treisman  is a great summary. The NPR audio story is accompanied by a written report. In that report, Treisman succinctly summarizes the methodology: https://www.npr.org/2023/01/26/1151332361/gel-nails-cancer-manicure-safe 1. Let's talk about science communication. The NPR story is accurate science reporting. However, most of the headlines don't mention that a) some of the evidence came from mice cells, and they measured cell mutations but not cancer.  2. Let's talk about factorial ANOVA The researchers used a 3 (cell types: human 1, hu...

NPR aired this story by Sarah Boden  about the relationship between risky financial behavior and dementia. It consists of Boden interviewing people caring for individuals with dementia and dementia researchers. Before the NPR story, Boden published a related piece to a Pittsburgh NPR station . The Pittsburgh piece is a more formal report with many links to helpful information. Among the research Boden describes is this study by Nicholas et al. (2020),  which finds that people exhibit poor financial decision-making up to six years before a dementia diagnosis. Here is a press release about the study, in case you want to give more advanced students a primer or earlier UG students a sheet for understanding the research.  The audio version of this story is very compelling. It includes interviews with several people who have been left heavily in debt because of poor decisions made by family members before their diagnosis. It also offers some solutions that could be implemented ...

ASIDE: THIS IS MY 500th POST. PLEASE CLAP. Efficacy data about a mental health intervention? Yes, please. The example has so much potential in a psych stats classroom. Or an abnormal/clinical classroom, or research methods. Maybe even human factors, because three numbers are easy to remember than 10? This post was inspired by an NPR story  by Rhitu Chatterjee. It is all about America's mental health emergency hotline's switch from a 10-digit phone number to the much easier-to-remember three digits (988), and the various ways that the government has measured the success of this change. How to use this (and related material) in class: 1) Assessment. In the NPR interview, the describe how several markers have improved: Wait times, dropped calls, etc.  Okay, so the NPR story sent me down a rabbit hole of looking for this data so we can use it in class. Here is the federal government's website about  988  and a link to their specific  988  performance data,...

Stats nerds: I'm warning your right now. This website is a rabbit hole for us, what with the interactive, customizable data visualizations. Please don't click on the links below if you need to grade or be with your kids or drive.  At a recent conference presentation, I was asked where non-Americans can find examples like the ones I share on my blog. I had a few ideas (data analytic firms located in other countries, data collected by the government), but wanted more from my answer.  BUT...I recently discovered this interactive from Our World in Data. It visualizes international data on human height, y'all  with so many different examples throughout. I know height data isn't the sexiest data, but your students can follow these examples, they can be used in a variety of different lessons, and you can download all of the data from the beautiful interactive charts. 1. Regressions can't predict forever. Trends plateau.  I'm using this graph to as an example of how a r...

Not all of our class examples should reject the null. Sometimes, you just need some non-significant data, small effect size data that doesn't detect a linear relationship. Such is the linear relationship between the number of calories and mg of caffeine in these 29 different treats provided by InformationIsBeautiful. InformationIsBeautiful provides that data , as do I .

Ok. Only some examples have to be profound. Sometimes, an example can break up a dry lesson like  z -scores.  This is my favorite z -score example . Ever. This current post may become my second favorite. The Pudding's Words Against Strangers is a game with four minute-long rounds. Each round asks for a type of word. Adjectives containing the letter "m." Verbs that contain an "r" and are precisely five letters long. That sort of prompt. Then you have one minute to type in as many of these words as possible. I recommend playing this on a computer, not a phone. If you are over 40. You are competing against one person on the internet.  After you play, your record is displayed as either: a) your over/under against the opponent b) your percentile score for everyone on the internet. Here is how I will use it in class. My students get into other games I've worked on in my classes ( Guess the Correlation ). I plan on asking my students to play this game, view their...

 I sneak attack my students with this correlation example. I ask them to analyze this data as a correlation and create a report describing their data. This is what the data looks like: I'll be honest, I mostly do this for my own amusement. HOWEVER: It does demonstrate that scatter plots are helpful when making sure that a correlation analysis/scatter plot may contain a non-linear relationship (see: Datasaurus ). If you want to make your own silly scatter plot for data analysis, I recommend Robert Grant's DrawMyData website for doing so.

Sometimes, you just need a new, simple example for a homework question or a class warm-up.   I eyeballed and entered the   data here  ( r   = -.55). Enjoy. I use this little example to explain to use the regression formula to make a prediction. Here are my slides .

Ages ago, I shared how I teach ANOVA at a conceptual level. I describe within and between group variance using beliefs about the human role in climate between and within different religious groups. This data is now old. And it described global warming, not climate change, which is a crucial language distinction. So you  can imagine my delight when Pew recently released  updated and improved data investigating this issue.  In my attempt to keep the mood light when discussing an example featuring 1) religion, 2) climate change, and 3) politics, I ask students to think about how many different opinions are probably represented around their family's Thanksgiving table. Despite having much in common as a family, like, perhaps, geography, shared stories, and religion, there are still a lot of within-group differences of opinion. This leads to a discussion about people of different religions having between and within group differences of opinion regarding beliefs about global cl...

YouGov gifts us with seasonal chi-square examples  with data on Thanksgiving food controversies. For example: How do people feel about marshmallows on sweet potato dishes? This doesn't look randomly distributed to me. Which is more beloved: Light or dark turkey meat? If you want examples for the chi-square test of independence, dig into the PDF containing ALL of this survey's data. The distribution of people who like cranberry sauce by age group does not appear random.