Main --> In the Classroom: Statistics

**Demonstrations**

**Random generator of practice problems ****(**website from Steve Carroll PhD)** **

It's a stats problem generator and a sort of 'statsopedia'. Here's how it works:

- Choose a statistic from the drop-down list at the top of the page.
- Click the "Give me a practice problem!" button. A new problem will appear in the workspace every time you push this button.
- Read the question, and then try to solve the problem by hand (using paper, a pencil, and a calculator).
- Click the "SHOW ANSWERS" button to check your work.
- If you are stuck along the way and need a little hint, many of the items listed in the workspace are "clickable". I've linked them to formulae and other useful information that will appear in this window.

**Hack Your Way To Scientific Glory (a ***p *- hacking demonstration)

(Hat tip to **Ali O'Malley** @ALOstasis )

Try different combinations of variables to get *p *< .05.

**Articles on teaching Statistics**

Attenders Versus Slackers: A Classroom Demonstration of Quasi-Experimentation and Self-Selecting Samples

Real examples pertaining to students in Stats and Methods classes (e.g., absences and test grades), are memorable for students. However, as Stellmack (2013) notes, the relationship between attendance and performance cannot be causal. Check out this article for more on teaching quasi-experimental designs.

Enhancing Table Interpretation Skills via Training in Table Creation

Karazsia (2013) found that students who learned to create APA-formatted tables performed significantly better on an assessment of table interpretation than did a comparison group of more advanced students who did not complete a table creation assignment. They also demonstrated transfer of knowledge from table creation to table interpretation, suggesting that such an active learning activity may be a promising technique for developing one aspect of quantitative

literacy.

Application Exercises Improve Transfer of Statistical Knowledge in Real-World Situations** **

Daniel and Braasch (2013) compared class sections that had application items and those that did not. They found that students who previously participated in the application exercise activities displayed a greater usage of statistical knowledge when answering transfer questions and mentioned real-world applications of statistics more often compared to control students. The take-home point is to consider using application items if your learning objectives include using statistics beyond your class.

Dance, Dance, Revolution! An Article on How to Use Gaming To Teach Factorial Design

Stansbury and Munro (2013) describe a study that assessed the effectiveness of using video games to teach research methods and statistics. They found increased knowledge retention over that of traditional methods using the video games. If you are a "gamer" and want to incorporate a unique teaching method, check out this article.

**Examples from the Internet**

*Visual representation of data (Thanks Jessica Hartnett via NotAwfulAndBoring.Blogspot)*

Data from a Dunkin Donuts survey. Have students compare how they should present the data and compare that with media presentations (see blog post here)

**Humor**

*Businessweek's "Correlation or Causation?" (via NotAwfulAndBoring.blogspot)*

This series of graphs illustrates instances when correlation does not equal causation.

*xkcd's "Boyfriend" (via NotAwfulAndBoring.Blogspot)*

This comic strip could be used to introduce outliers, error bars, box plots, statistical significance, and operational definitions (see blog post here).

*xkcd's "Significant" ( via NotAwfulAndBoring.Blogspot)*

This comic strip could be used to introduce statistical significance, nonsignificance, alpha levels, conclusions from data, causal language, and so on (see blog post here).

xkcd's "Convincing" (*via NotAwfulAndBoring.Blogspot)*

* This comic strip touches upon APA formatting for graphs (see blog post here).*

*Matthew Freeman's "**A visual comparison of normal and paranormal distributions" **(**via NotAwfulAndBoring.Blogspot)*

*Jess Hagy's "This Is Indexed"** **(**via NotAwfulAndBoring.Blogspot)*

* Hagy uses simple graphs to describe her everyday experience. A statistics instructor could use her graphs to describe psychological phenomena like linear relationships and shared variance. *

**In-class activities**

*Monty Hall Problem *(Program and PowerPoint presentation courtesy of Mike Williams via TIPS 06/01/2014)

Mike writes: "I wrote a standalone program to simulate the Monty Hall problem. This problem is a good example of the contrast between intuitive and actual probability. It is a great exercise for Stats classes when you cover probability. If you have not heard of it, there are a number of web sites that explain it. There are also other web-based simulators. I could not find one that allowed the user to set up their own *n* of trials so I wrote this one in Livecode."

Presentation:

http://www.learnpsychology.com/monty/Monty_Hall_Presentation.pptx

Program

Mac Version:

http://www.learnpsychology.com/monty/Monty_Hall_Problem.zip

PC Version:

http://www.learnpsychology.com/monty/Monty_Hall_Problem.exe

*Standard Error (Demonstration courtesy of John Kulig via TIPS.)*

An easy non-computerized demo is have everyone in the class put their height in inches or cm on a slip of paper into a hat, and then sample one by one and plot them on the whiteboard (sample with replacement). How you "figure" the standard deviation depends. I like to have the actual values in advance, but if not, the "idea" of the standard deviation can be eye-balled from the plot, as well as the mean.

Then you can do the same thing by having someone take out 2 slips of paper at a time and get repeated averages of two heights, plotting the averages on a separate plot on the whiteboard. Again, I like to know the means and standard deviations in advance so I can stack one plot above the other with the means and x-axis values lining up. It can be done with means of 4 or 8 too, but that takes more time. If done carefully, it's easy to see that roughly 2/3 (68%) of X fall within one SD on the X plot, and 2/3 of means lie within one SE on the means plot - with the usual caveat "individual results may vary".

When I do this in a stats class (different audience), I sometimes generate random data on MINITAB for a few different sample sizes and pop the histograms out of the computer, and often use sample sizes 1 to 4 to 16, as I can wing the standard error in my head (SE gets chopped in half every time N increases 4-fold, so, if you use IQ scores you can jump from 15 to 7.5 to 3.75 without calculators or computers).

If all else fails, my moment of Zen (I do one every stat class). On this topic: "Standard Deviation is to X as Standard Error is to X bar".

Using polling data to demonstrate sampling error, margin of error, and confidence intervals * **(**via NotAwfulAndBoring.Blogspot)*

**Online Resources **(courtesy of Leigh Harrell Williams via STP Facebook Group, 1/8/14)

*The Journal of Statistics Education *has a section on Data Sets and Stories. Check out these resources here and here.

See also CAUSEweb.org resources here.

**Statistics in the News**

NPR's "Data linking aspartame to cancer risk are too weak to defend, hospital says": A news story about how one hospital's PR department overstated research findings, which forced the researchers to publish their own press release urging the public to not read too much into their research. A good way of demonstrating a) Type I Error as well as b) the interplay between the media and science (via NotAwfulAndBoring.blogspot)

## Comments (0)

You don't have permission to comment on this page.