Question
Two statisticians at Autodesk were inspired by this man's work to create the “Datasaurus Dozen,” which includes graphs shaped like an ellipse, a star, and a dinosaur. For 10 points each:
[10h] Name this statistician, who created four data sets with nearly identical mean, variance, correlation, and linear regression line, but very different underlying distributions.
ANSWER: Francis Anscombe
[10m] The batting averages of Derek Jeter and David Justice are often used to show this phenomenon, in which a trend that appears in several groups of data is reversed when the groups are combined.
ANSWER: Simpson's paradox [or the Yule-Simpson effect or amalgamation paradox or reversal paradox; prompt on the ecological fallacy]
[10e] This mathematician expressed a similar idea to Simpson’s paradox in 1899, 52 years before Simpson. The most common way of quantifying the strength of a linear correlation is with his namesake “r.”
ANSWER: Karl Pearson [accept Pearson’s r]
<BB>
Summary
| 2023 BHSU @ Maryland | 03/11/2023 | Y | 1 | 0.00 | 0% | 0% | 0% |
| 2023 BHSU @ Northwestern | 02/25/2023 | Y | 5 | 20.00 | 60% | 80% | 60% |
| 2023 BHSU @ Sheffield | 04/15/2023 | Y | 2 | 15.00 | 100% | 50% | 0% |
| 2023 BHSU @ Waterloo | 04/15/2023 | Y | 3 | 23.33 | 100% | 100% | 33% |
| 2023 BHSU @ Yale | 04/08/2023 | Y | 3 | 13.33 | 100% | 33% | 0% |
Data
| Michigan | Epic Games | 0 | 10 | 0 | 10 |
| Maryland B- | WUSTL | 10 | 10 | 10 | 30 |
| Mojo Shojo | Chicago B+ | 0 | 0 | 0 | 0 |
| Chicago A | Northwestern | 10 | 10 | 10 | 30 |
| Amartya Senpai Notice Me | Maryland B- | 10 | 10 | 10 | 30 |