This app focuses on tests for proportions in a sports context (basketball free throw shooting). The app illustrates how a change in the population caused by filtering can change the results and also illustrates the difference between p, p̂, and p0.
Category / Statistical Inference
Hypothesis Testing Game
This app quizzes your knowledge of hypothesis testing concepts using a tic-tac-toe game format.
Inference for Means
The app requires students to engage with inference scenarios for a mean (or difference in means) in context. Users will explore the behavior of confidence intervals for a single mean and two sample tests for the difference in means as the level and sample size changes.
Inference for Proportions
The app requires students to engage with inference scenarios for a proportion (or difference in proportions) in context. Users will explore the behavior of confidence intervals for a single proportion and two sample tests for the difference in proportions as the level and sample size changes.
Significance Testing Caveats
This app examines the distribution of p-values across samples to illustrate three key caveats of significance testing (the multiple testing caution; the large sample caution; and the small sample caution).
Simpson’s Paradox
In this app you will explore Simpson’s paradox. Simpson’s paradox is a phenomenon in which a trend appears in different groups of data but disappears or reverses when these groups are combined.
Simulations in Context
Learn how simulations come together in specific scenarios. Read through context and link key terms to their meanings. Then create a simulation that accurately reflects the situation.
Testing and CI Relationship
This app explores real datasets to look at inferences for a single mean and how significance tests relate to confidence intervals.
Waiter Experiment
This app demonstrates the reasoning of a two-sample t-test in the context of examining whether a waiter giving a table candy or not affects their tip percentages.
Wilcoxon Rank Tests
This app allows students to explore the concept of two non-parametric tests called Wilcoxon Signed Rank Test for one sample data or two sample unpaired data and Wilcoxon Rank Sum Test for two sample paired data.