Monday, January 30, 2017

Shaver's Female dummy makes her mark on male-dominated crash tests

Here is another example of why representative sampling MUST include women. For years and years, car crash test dummies for adults were all based upon the 50th percentile male. As such, even in vehicles with high safety ratings, women still has higher rates of certain injuries (head, neck, pelvis) than men. In fact, the article cites research that found that belted female car occupants in accidents have a 47% higher chance of suffering a serious injury and a 71% higher chance of suffering a moderate injury compared to men in a car.

http://leevinsel.com/blog/2013/12/30/why-carmakers-always-insisted-on-male-crash-test-dummies

I wrote a previous blog post about this video that outlines how using only male rats for pharmaceutical research lead to problems with disproportionately high numbers of side effects in female humans. And this NPR story details changes to federal rules in order to correct for this issue with animal testing.

How to use in class:

-Inappropriate sampling is hurting and killing women.
-Many test dummies are constructed using descriptive statistics as to create an "average" human. The most often used dummy represents a 50th percentile male.
-Pair it with my articles/stories/videos about the lack of female representation in pharmaceutical testing and you've got yourself a nice class discussion about representative sampling and subtle but dangerous forms of sexism (Why is a average male considered an average human? How can this problem be addressed?).

Monday, January 23, 2017

DeBold & Friedman's "Battling Infectious Diseases in the 20th Century: The Impact of Vaccines"

The folks at Wall Street Journal took CDC disease data (by state, by year, courtesy of Project Tycho) as well as information on when various vaccines were introduced to the public. And the data tells a compelling story about the importance of vaccinations. Below, the story of measles.






How to use in class:
-Using archival data to educate and make a point (here, vaccine efficacy)
-Visualizing many data points (infections x state x year) effectively
-Interactive: You can cursor over any cube to see the related data. Below, I've highlighted Pennsylvania data from 1957.





-Since  you can cursor over any data point to see the data, you can ask your students to pull data for use in class.
-The present data was draw from Project Tycho, a University of Pittsburgh initiative to better share public health data. This resource may be useful to your classes as well.
-This data is good for Stats class, as well as Developmental, Health, Public Health, etc.


Monday, January 16, 2017

Our World in Data website

Our World in Data is an impressive, creative-commons licensed site managed by Max Roser.

And it lives up to its name. The website provides all kinds of international data, divided by country, topic (population, health, food, growth & inequality, work and life, etc.), and, when available, year. It contains it's own proprietary data visualizations, which typically feature international data for a topic. You can customize these visualizations by nation. You can also DOWNLOAD THE DATA that has been visualized for use in the class room.

Much of the data can be visualized as a map and progress, year by year, through the data, like this data on international human rights.
https://ourworldindata.org/human-rights/ 


https://ourworldindata.org/human-rights/

There are also plenty of topics of interest to psychologists who aren't teaching statistics.

For example, international data on suicide:

Data for psychology courses...https://ourworldindata.org/suicide/

Working hours for I/O psychologists:
https://ourworldindata.org/working-hours/

Data on specific hate crimes (here, lynching) for social psychology:
https://ourworldindata.org/treatment-of-minorities


How to use in class:
-Not all graphs are appropriate for all data and all of the ways we use data. When might the mapping of data work well? When would it be better to show changes in data per country over time?
-For each of the visualizations, you can also click on "DATA" if you want your students to work with the data on their own.
-The website beautiful demonstrates how to tell a story and build an argument using descriptive data. I know that I emphasized the data visualization/data download piece, but for each of the subtopics, a story is told. In addition to using their own visualizations, the website frequently references and cites outside data sources and visualizations. 

Monday, January 9, 2017

Parents May Be Giving Their Children Too Much Medication, Study Finds

Factorial ANOVA example ahead! With a lovely interaction. And I have a year old and a 4.5 year old and they are sickly day care kids, so this example really spoke to me.

NPR did a story about a recent publication that studied how we administer medicine to our kids and provides evidence for a few things I've suspected: Measuring cups for kid medicine are a disaster AND syringes allow for more accurate dosing, especially if the dose is small.

The researchers wanted to know if parents properly dosed liquid medicine for their kids.

The researchers used a 3 (dosage, 2.5, 5.0, 7.5 ml) x 3 (modality: small syringe, big syringe, medicine cup) design. They didn't use factorial ANOVA in their analysis, this example can still be used to conceptually explain factorial ANOVA.

Their findings:



How to use in class:

-An easy to follow conceptual example of factorial ANOVA (again, they didn't use that analysis in the original paper, but the table above illustrates factorial ANOVA beautifully).
-An easy to follow example of what an interaction can look like.
-An example that is medical in nature
-An example that might reach your non-traditional and student parents
-Interesting methodology: They used for reals parents using for reals medical implements.
-How should doctors use this data? How about pharmacists and parents? What sort of implement is associated with the least overall error?

Sunday, January 1, 2017

Pokemon Go and physical activity

In honor of the New Year, a post about health. 

A team of researchers from Harvard made a brief video that describes their recent publication. The video includes discussion about their hypothesis generation, methodology, and research findings. 

Their research question: Does the game Pokemon Go actually improve the health of users?


How to use this video in your class:

-This is an easily understood research project to share with your RM students. It also goes into detail about the statistics used for analysis.

-And the researchers, from fancy-pants Harvard, aren't afraid of being a bit silly and having fun as researchers. As demonstrated by the below images from the video:

This guy. Seriously. I hope to some day love my data as much as he loves his data.


And they made graphs using Pokemon balls


-How do we get our research ideas? Sometimes, from observations about every day living. This research was inspired by the Pokemon Go phenomena. I try to convince my students that many research ideas are the result of genuine curiosity about the world, and I think this does a good job of illustrating it.

-One of the co-authors describes the methodology: How the recruited and chose participants, describe the regression model they used, factored out seasonal differences the could affect how much time people spend outside.

-It is a video.

-Accessible example of quasi-experimental methods to create an a control group and an experimental group.

-You could use this video as the Cliff Notes to accompany the actual research paper. For students who are new to reading source material, this might be a soft step into navigating publications.

-Could be good for human factors or health psychology classes in addition to stats/RM.