This site did a lot of data visualization on many hot button topics. They provide the raw data that they used to create their graphs at this page. These data sets are kept in Google Doc spreadsheets.
The Comprehensive Epidemiologic Data Resource is a collection of data sets. It includes definitions of each variable in the data set. It requires a login to retrieve the data sets. Registering involves giving your name and address and the name of the study and a detailed description of the intended use of the data.
This complete lesson plan, which includes assessments, is based upon a data set partially discussed in the article "Female Hurricanes are Deadlier than Male Hurricanes." The data set contains archival data on actual fatalities caused by hurricanes in the United States between 1950 and 2012. Students analyze and explore this hurricane data in order to formulate a question, design and implement a plan to collect data, analyze the data by measures and graphs, and interpret the results in the context of the original question.
The textbook, "Statistics: Unlocking the Power of Data," by Lock, Lock, Lock, Lock, and Lock, webpage has a collection of data sets which are used in their textbook. Even without the textbook, the variables are well named, and it is relatively easy to tell what the variables represent.
This issue contains articles about binomial confidence intervals; the team effect in stock car racing; using multiple tests (one-sample t-test and sign test); the "two-envelope exchange paradox" (similar to the Monty Hall problem) with discussions of expectation, likelihood, and inference; regression line vs. trend line; calculations of standard normal table values and pi; teaching at a small liberal arts college; modeling extreme events.
This issue contains articles about steroids in baseball; finding ways to make learning statistics fun; an interview with Joan Garfield about Statistics Education; an introduction to response surface methodology; and a look at the vocabulary used in experimental design.
This issue contains articles on: The advantages and pitfalls of using online panel research, including a discussion of improving data quality and designing the survey research strategically, sequential sampling and testing in a "simple against simple" situation, including a description of Abraham Wald's historical and theoretical contributions to the theory, and R code for running simulations, and the experience and results of an exit poll conducted by two students in Washington D.C. during the 2008 presidential election.
This issue contains an article that provides an example of a paired samples test related to flying and gliding. It also includes an article about understanding confounding from lurking variables using graphs. Other articles include: a short description about what the t-tests actually tests, an interview with David Moore about why 30 is the "magic" number, a discussion about whether or not outliers should be deleted from a data set, a discussion of observational studies, and a simulation piece about random numbers from non-random arithmetic.
This issue contains an interview with Sallie Keller-McNulty and an article about which came first -- the chicken or the egg. Other articles include a discussion related to an AP Statistics example of seeing the trees for the forest (this focuses on understanding variability between groups and within groups), a discussion of how high r can go, a simulation piece focused on shrinking students, poisoned children, and bootsraps, and an example of a permutation test of the Challenger O-Ring data.
