Skip to main content

Posts

Pedagogy article recommendation: "Introducing the new statistics in the classroom."

I usually blog about funny examples for the teaching of statistics, but this example is for teachers teaching statistics. Normile, Bloesch, Davoli, & Scheer's recent publication, "Introducing the new statistics in the classroom" (2019) is very aptly and appropriately titled. It is a rundown on p-values and effect sizes and confidence intervals. Such reviews exist elsewhere, but this one is just so short and precise. Here are a few of the highlights: 1) The article concisely explains what isn't great or what is frequently misunderstood about NHST. 2) Actual guidelines for how to explain it in Psychological Statistics/Introduction to Statistics, including ideas for doing so without completely redesigning your class. 3) It also highlights one of the big reasons that I am so pro-JASP: Easy to locate and use effect sizes.

Hurricane Confidence Intervals

UPDATE 10/5/22: No paywall article that conveys the same information:  https://www.msn.com/en-us/weather/topstories/cone-of-confusion-why-some-say-iconic-hurricane-map-misled-floridians/ar-AA12Bqyp Did you know that hurricane prediction maps are confidence intervals? This is one of my examples that serves more as a metaphor than a concrete explanation for a statistic, so bear with me. The New York Times created a beautiful, interactive website (it looked exceptionally sharp on my phone). The website attempts to explain what hurricane prediction maps tell us, versus how people interpret hurricane prediction maps. The website is at NYT, so you probably will hit a paywall if you have already viewed three stories on the NYT website in the last month. As such, I've included screenshots here. Here is a map with the projected hurricane path. People think that the white line indicates where the hurricane will go, and the red indicates bad weather. They also think that the broader path...

Transforming your data: A historical example

TL:DR: Global water temperature data from <1940 was collected by sailors collecting buckets of water from the ocean and recording the temperature of their bucket water. But some recorded data was rounded (thanks, Air Force!). Then, researchers had to transform their data. ^Go to the 3 minute mark to see the bucket-boat-water-temperature technique in action Here is the original research,  published in Nature . NPR covered the research article . Reporter Rebecca Hersher didn't discuss the entire research paper. Instead, she told the story of how the researchers discovered and corrected for their flawed ocean water temperature data. This story might be a little beyond Intro Stats, but it tells the story of messy, real archival data used to inform global climate change and b) introduces the idea of data transformations. Below, I will highlight some of the teaching items. Systematic bias: The data were all flawed in the same way as they were transcribed without any da...

CNN's The most effective ways to curb climate change might surprise you

CNN created an interactive quiz that will teach your students about a) making personal changes to support the environment, b) rank-order data, and c) nominal data. https://www.cnn.com/interactive/2019/04/specials/climate-change-solutions-quiz/ The website leads users through a quiz. For eight categories of environmental crisis solutions, you are asked to rank solutions by their effectiveness. Here are the instructions: Notice the three nominal categories for each solution: What you can do, What industries can do, What policymakers can do. Below, I've highlighted these data points for each of the "Our home and cities" solutions. There are also many, many examples of ordinal data. For each intervention category, the user is presented with several solutions and they must reorder the solutions from most to least effective. How the page looks when you are presented with solutions to rank order: The website then "grades" your respons...

Mother Jones' mass shooting database

Mother Jones' magazine maintains a database of mass shooting events in the United States. 25 variables are collected from every shooting MJs collects 25 variables from every shooting. Below, I've included their own description of the purpose of their database: How to use in class: Within this data is an example for every test we teach in Introduction to Statistics. Correlation/Regression Fatalities Injuries Age of shooter Year of shooting Chi-square Shooter gender Shooter ethnicity Mass or Spree shooting Were the weapons obtained legally? ANOVA Shooter ethnicity T-test Mass or Spree shooting Were the weapons obtained legally? Data Cleaning  Some of these columns need some work before analysis. For instance, there are multiple weapons listed under "Weapon Type". Which is reasonable, but not helpful for descriptive data. You could walk your students through the process of recoding that column into multiple columns. You could also expl...

Passion driven statistics

Passion-Driven Statistics is a grant-funded, FREE resource that teaches the basic of statistics, including the basics of all of the stuff you need to know to conduct good research (data management, literature review, etc.). It bills itself as "project-driven" and is super, duper applied, which is an approach I love. You can download the whole stinking book  or view it online. And the PDF is concise and short, given the amount of material it covers. Why so short? Because it is lousy with links to Youtube videos, mini-assignments, instructions for reporting different statistical tests, etc.  I also love this resource because it contains a lot of good information for novices that I haven't seen packaged this way or in one place: Important lessons pertaining to the research process and data collection: The book is written to take you through a research project, and includes guidance for performing a literature review, writing a sound codebook, data management, etc. ...

The Washington Post, telling the story of the opioid crisis via data

I love dragging on bad science reporting as much as anyone, but I must give All Of The Credit to the Washington Post and its excellent, data-centered reporting on the opioid epidemic . It is a thing of beauty. How to use in class: 1) Broadly, this is a fine example of using data to better understand applied problems, medical problems, drug problems, etc. 2) Specifically, this data can be personalized to your locale via WaPo's beautiful, functional website . 3) After you pull up you localized data, descriptive data abound...# of pills, who provided them, who wrote the scripts (y'all...Frontier Pharmacy is like two miles from my house)...   4) Everyone teaches about frequency tables, right? Here is a good example: 5) In addition to localizing this research via the WaPo website, you can also personalize your class by looking for local reporting that uses this data. For instance, the Erie newspaper reporter David Bruce reported on our local problem ( .pdf of the...

Seagull thievery deterrent research provides blog with paired t-test example.

I have spent many a summer day at Rehoboth Beach, DE. The seagulls there were assholes. They would aggressively go after food, especially your bucket of Thrasher's french fries. Apparently, this is a global problem, as a group of stalwart researchers in the UK attempted to dissuade gulls from stealing french fries by staring those sons-of-a-gun down . Researchers Goumas, Burns, Kelley, and Boogert shared their data . And it makes for a nice t-test example. 1. The Method section is hilarious and true. 2. Within-subject design: Each seagull was observed in the stare down and non-staredown condition 3. Their figure is a nice example of the data visualization trend of illustrating individual data points. 4. The researchers shared their data. You can download it here . The Goumas et al. supplemental data can be used as a paired t-test example, t (18) = 3.13, p = .006, d = 0.717.

Health and Human Service videos: Explaining research to participants

The U.S. Department of Health and Human Services produced a bunch of great videos to explain topics related to human subject research . The videos were created as part of a broader outreach effort intent on  explaining the research process to research participants .  I think they would fit right into a Research Methods course. Topics include: IRBs: Research design: There is also a specific video explaining social science research: All of the videos (along with handouts) are available here . All videos have closed-captions as well as Spanish versions

The Pudding's Colorism

Malaika Handa , Amber Thomas , and Jan Diehn created a beautiful, interactive website, Colorism in High Fashion . It used machine learning to investigate "colorism" at Vogue magazine. Specifically, it delves into the differences, over time, in cover model color but also how lighting and photoshopping can change the color of the same woman's skin, depending on the photo. There are soooo many ways to use this in class, ranging from machine learning, how machine learning can refine old psychology methodology, to variability and within/between-group differences. Read on: 1. I'm a social psychologist. Most of us who teach social psychology have encountered research that uses magazine cover models as a proxy for what our culture emphasizes and values ( 1 , 2 , 3 ). Here, Malaika Handa, Amber Thomas, and Jan Diehn apply this methodology to Vogue magazine covers. And they take this methodology into the age of machine learning by using k-means cluster and pixels to deter...

Interactive NYC commuting data illustrates distribution of the sampling mean, median

Josh Katz and Kevin Quealy p ut together a cool interactive website to help users better understand their NYC commute . With the creation of this website, they also are helping statistics instructors illustrate a number of basic statistics lessons. To use the website, select two stations... The website returns a bee swarm plot, where each dot represents one day's commuting time over a 16-month sample.   So, handy for NYC commuters, but also statistics instructors. How to use in class: 1. Conceptual demonstration of the sampling distribution of the sample mean . To be clear, each dot doesn't represent the mean of a sample. However, I think this still does a good job of showing how much variability exists for commute time on a given day. The commute can vary wildly depending on the day when the sample was collected, but every data point is accurate.  2. Variability . Here, students can see the variability in commuting time. I think this example is e...

Do Americans spend $18K/year on non-essentials?

This is a fine example of using misleading statistics to try and make an argument. USA Today tweeted out this graphic , related to some data that was collected by some firm. There appear to be a number of method issues with this data, so a number of ways to use this in your class: 1) False Dichotomy:  Survey response options should be mutually exclusive. I think there are two types of muddled dichotomies with this data: a) What is "essential"? When my kids were younger, I had an online subscription for diapers. Those were absolutely essential and I received a discount on my order since it was a subscription. However, according to this survey dichotomy, are they an indulgence since they were a subscription that originated online. b) Many purchases fall into multiple categories. Did the survey creators "double-dip" as to pad each mean and push the data towards it's $18K conclusion? Were participants clear that "drinks out with frien...

Pew Research's "Gender and Jobs in Online Image Searches"

You know how every few months, someone Tweets about stock photos that are generated when you Google "professor"? And those photos mainly depict white dudes? See below. Say "hi" to Former President and former law school professor Obama, coming it at #10, several slots after "novelty kid professor in lab coat". Well, Pew Research decided to quantify this perennial Tweet, and expand it far beyond academia. They used Machine Learning to search through over 10K images depicting 105 occupations and test whether or not the images showed gender bias.  How you can use this research in your RM class: 1. There are multiple ways to quantify and operationalize your variables . There are different ways to measure phenomena. If you read through the report, you will learn that Pew both a) compared actual gender ratios to the gender ratios they found in the pictures and b) counted how long it took until a search result returned the picture of a woman for a given j...