Alexis Diamond

One Trial, Many Trials

Students run a simulated tutoring experiment again and again, and see that any single RCT estimate misses the true effect while the average of many lands on it. They also see the spread of estimates shrink with the square root of n. Interactive dials drive R code cells, and students then complete the key calculations themselves.

By Alexis Diamond

Which Effect Does the Regression Estimate? Controlling for a confounder and the ATE, ATT and ATC

A hundred farmers, an irrigation pump, and the coefficient you get when you control for wealth: does the regression estimate the ATE, ATT or ATC? This revision makes every control shared state so breakout teammates see the same screen.

By Alexis Diamond

Scavenger Hunt: King Tomz Wittenberg (2000)

Students read the model's expected probability of voting by age for one hypothetical person, with confidence bars, and learn the curve is about a person you define while the bars show uncertainty in the model. Pinned curves and the break-it toggle are now shared state, so teammates see the same page.

By Alexis Diamond

Rich and Poor Farmers: What Does Regression Recover?

A Coding workbook in R. Students simulate 100 farmers with both potential outcomes, compute the naïve gap, ATE, ATT, ATC and selection bias, then see that a regression with a control matches none of them while an interaction model does. A final part contrasts confidence and prediction intervals.

By Alexis Diamond

Lord's Paradox: Two Statisticians, One Dataset

Two statisticians analyse the same six students' weights and reach opposite conclusions. Students compute both analyses in R and then work out what each one assumes about the missing counterfactual.

By Alexis Diamond

lalonde

By Alexis Diamond

selection bias

By Alexis Diamond

sutva violation

By Alexis Diamond

Python together: simulating coin flips

Groups write and run Python together in the browser: simulate coin flips, find streaks, and use pandas on a class dataset to judge whether a coin is fair.

By Alexis Diamond

R together: is this coin fair?

Groups write and run R together in the browser: simulate coin flips, then use read.csv, aggregate and binom.test on a class dataset to judge whether a coin is fair.

By Alexis Diamond

The Logistic Squeeze (remix)

A logistic regression is a straight line on the logit scale, squeezed through the logistic function into a probability. This version adds a comprehension question and a reflection question at the bottom, each with a text box whose answer is captured in state, and fixes a colour-contrast failure.

By Alexis Diamond