Introduces the distinction between quantitative and categorical variables through their very different appearances in a point plot.
Using distributions to examine which values are common and which are rare.
Normal distributions are a *family*. The specific members of the family are identified by two parameters: the mean and the standard deviation.
Introduces terms such as skew, bi-modal, and flat, by reference to the difference of the actual variable from a theoretical normal distribution.
Visualizing sampling variation in the difference between two groups.
Describes the desired behavior of a confidence interval, that is, how to know whether a procedure produces a valid confidence interval.
Using one-sample confidence intervals on the mean to decide if there's good evidence that two means are different. Statistical experts know to use the two-sample t-test for such problems, but best to build up intuition first and then add mathematical refinements later. And, you'll be able to see for yourself whether the refinements have any practical impact.
Discussion topics to introduce linear regression to your class.
Translating a regression line into a description in everyday terms
Reasons to identify one variable as the response and another as the explanatory.
Causality as a reason to identify one variable as the response and another as the explanatory.
Using R-squared to quantify how much of the variation in a response variable is accounted for by explanatory variables.
A confidence interval will cover the population parameter with the right frequency only if the sample is unbiased. This lesson explores sampling bias. (NOTE: The app used here is in the original style of the Little Apps. It has not yet been translated into the current system used for the Apps.)
The generic form of a Little App Activity document. For reference when adding new activities to the site.