Monday, July 25, 2016

Wilson's "America’s Mood Map: An Interactive Guide to the United States of Attitude"

Here is a great example of a several different topics, featuring an engaging, interactive map created by Time magazine AND using data from a Journal of Personality and Social Psychology article.

Essentially, the authors of the original article gave the Big Five personality scale to folks all over the US. They broke down the results by state. Then Time created an interactive map of the US in order to display the data.

http://time.com/7612/americas-mood-map-an-interactive-guide-to-the-united-states-of-attitude/

How to use in class:


Monday, July 18, 2016

Data USA

Data USA draws upon various federal data sources in order to generate visualizations about cities and occupations in the US. And it provides lots of good examples of simple, descriptive statistics and data visualizations.

This website is highly interactive and you can query information about any municipality in the US. This creates relevant, customized examples for your class. You can present examples of descriptive statistics using the town or city in which your college/university/high school is located or you could encourage students to look up their own hometowns. Data provided includes job trends, crime, health care, commuting times, car ownership rates...in short, all sorts of data.

Below I have included some screen shots for data about Erie, PA, home of Gannon University:

The background photo here is from the Presque Isle, a very popular state park in Erie, PA. And, look, medians!

Monday, July 11, 2016

Quealy & Sanger-Katz's "Is Sushi ‘Healthy’? What About Granola? Where Americans and Nutritionists Disagree"

This article from the NYT is based upon a survey. That survey asked a bunch of nutritionists if they considered certain foods healthy. Then they asked a bunch of every day folk if they considered the same foods to be healthy.

Then they generated the percentage of each group that considered the food healthy. And the NYT put the nutritionist responses on a Y-axis, and commoners on the X, and made a lovely scatterplot...

Nutritionists and non-nutritionists agree that chocolate chip cookies are not healthy. However, nutritionists are far more critical of American cheese than are non-nutritionists. 


...and provided us with the raw data as well.


Monday, July 4, 2016

Understanding children's heart surgery outcomes

Good data should inform our decisions. Even really stressful decision. This site demonstrates this beautifully by providing UK pediatric hospital survival rates to aid the parents of children undergoing heart surgery.

The information is translates for lay people. They present statistical ideas that you and your students have heard of, but without a lot of statistical jargon. The data is also presented very clearly. They present detailed hospital survival rates which includes survival ranges:



So, it contains data from a given time period. It includes the actual mortality rate as well as a range that is likely to contain the true mortality rate. Essentially, confidence intervals but not exactly confidence intervals.

In addition to this more traditional presentation of the data, the survival ranges are explained in greater detail in a video. I think this video is useful in that it explains distribution of the sample mean and how to use these in order to make an estimate of true survival rates.


Examples for the classroom:

-Sample v. population: A 30 day survival sample rate is just a sample and does not necessarily reflect the True outcome data.
-Variability: They explain that the data contains variability due to the fact that all patients have different pre-existing conditions/personal odds of survival.
-Confidence intervals-ish: When they describe a given survival rate, they use that within the context of that hospitals predicted range. These "predicted ranges" are confidence intervals. They never, ever call them confidence intervals because that phrase means nothing to a lay person.
-When computing the predicted range, they create multiple models of possible samples that could have been collected. So the sampling distribution of the sample mean.
-The blue bar is the 95th percentile. The gray bar is the 99.8th percentile.
-Again, data shouldn't be collected and left on a shelf or in a difficult to follow medical journal. It should be shared with the people that need it the most so they can make an informed decision about their child's health.