Skip to main content

Posts

io9.com's "Packages sealed with "Atheist" tape go missing 10x more often than controls"

I originally came across this story via io9.com . More information from the source is available here . Essential, these high-end German shoes are made by a company of devoted atheists. They even have their mailing materials branded with "atheist". And they had a problem with their packages being lost in by the USPS. They ran a wee experiment in which they sent out packages that were labeled with the Atheist tape vs. not, and found that the Atheist packages went missing at a statistically higher rate than the non-denominational packages. I think this could be used in the classroom because it is a pretty straight-forward research design, you can challenge your students to question the research design, simply challenge your students to read through the discussion of this article at the atheistberlin website, introduce your students to Milgram's "lost letter" technique and other novel research methods. Edit: 3/9/2020 If you want to delve further into...

Jess Hagy's "This is Indexed"

Jess Hagy illustrates her observations about life using simple graphs . I use her illustrations in order to provide examples to my students. Does this illustrate a positive or negative correlation? Property of Jess Hagy Would a correlation detect this relationship? Why or why not?  Property of Jess Hagy According to this diagram, what two different factors may account for the shared variance between the two variables?  Property of Jess Hagy

Statistics Meme 2

After months of hard work, hypothesizing, data collection...then you hold your breath and click "OK" in SPSS... From "I fucking love science" FB page

Shameless self-promotion

Here is a publication  from Teaching of Psychology in which I outline not one, not two, not three, but FOUR free/cheap internet based activities to be used in statistics/research methods classes. (If you have access to ToP publications, you can also get it here .)

Media Matter's "Today in dishonest Fox News charts"

How to lie with accurate data...note how Fox News used a "creative' graph in order to make an 8.6% unemployment rate look like a 9% unemployment rate. Full story available at Media Matters (which, admittedly, is very left-leaning). From Media Matters

io9's "You're bitching about the wrong things when you read an article about science"

Colorful title aside,  this article  teaches critical thinking when analyzing scientific writing for validity and reliability. Property of io9.com As a Social Psychologist, I'm especially grateful that they covered the "Study of Duh" criticism. It also adresses the difference between bad science and bad journalism and why one needs to see the source material for research before they are in a position to truly evaluate a study.

Newsweek's "What should you really be afraid of?" Update 6/18/15

I use this when introducing the availability heuristic in Intro and Social (good ol' comparison of fatal airline accidents vs. fatal car crashes), but I think it could also be used in a statistics class. For starters, it is a novel way of illustrating data. Second, you could use it to spark a discussion on the importance of data-driven decision making when it comes to public policy/charitable giving. For instance, breast cancer has really good PR, but more women are dying of cardiovascular disease...where should the NSF concentrate its efforts to make the biggest possible impact? Property of Newsweek More of same from Curiosity.com... curiosity.com  https://pbs.twimg.com/media/Bur_W0hCMAAOidE.png

The Onion's "Are tests biased against students who don't give a shit?"

The language blue, so use at your own risk...  but this faux debate is hilarious . I use it in my I/O and statistics classes to illustrate reliability, psychometric concerns related to test takers who are not totally engaged in their task, etc.

Franz H. Messerli's "Chocolate consumption, cognitive function, and Nobel Laureates"

A chocolate study seems very appropriate for the day after Easter. Messerli's study found a strong and positive correlation between a nation's per capita chocolate consumption and the number of Nobel prizes won by that nation (see graph below). The research article is a pretty straight forward: The only statistical analysis conducted was a correlation, the journal article is very short, and it used archival data. As such, you can use this example to illustrate correlation and archival data as well as the dread "third variable" problem (by asking students to generate variables that may increase chocolate consumption as well as top-notch research/writing/peace/etc.). Property of Messerli/New England Journal of Medicine

Statistics Meme I

from http://hello-jessica.tumblr.com Who knew that Zoidberg was an ad hoc reviewer?

Happy St. Paddy's Day!

For the original, click here . Property of history.com

Jessie Spano's Caffeine Intake

In honor of Daylight Savings Time and my own caffeine addiction. This will always be the funniest graph ever, p < .05. Property of Nathaniel James