Question

Read the excerpt from Steven D. Levitt and Stephen J. Dubner’s Freakonomics.

Let’s now consider the following statistic, which represents the hundreds of matches in which a 7–7 wrestler faced an 8–6 wrestler on a tournament’s final day:

7–7 WRESTLER’S PREDICTED WIN PERCENTAGE AGAINST 8–6 OPPONENT: 48.7
7–7 WRESTLER’S ACTUAL WIN PERCENTAGE AGAINST 8–6 OPPONENT: 79.6

So the 7–7 wrestler, based on past outcomes, was expected to win just less than half the time. This makes sense; their records in this tournament indicate that the 8–6 wrestler is slightly better. But in actuality, the wrestler on the bubble won almost eight out of ten matches against his 8–6 opponent. Wrestlers on the bubble also do astonishingly well against 9–5 opponents:

7–7 WRESTLER’S PREDICTED WIN PERCENTAGE AGAINST 9–5 OPPONENT: 47.2
7–7 WRESTLER’S ACTUAL WIN PERCENTAGE AGAINST 9–5 OPPONENT: 73.4

The authors use the statistics in this excerpt to
describe the complexity of sumo scorekeeping.
explain in detail the intricacies of sumo wrestling.
make a case for the idea that sumo wrestling is rigged.

Answer 1

make a case for the idea that sumo wrestling is rigged.

The excerpt shows that 7–7 wrestlers win far more often than their expected win probabilities (about 79.6% vs ~48%), which the authors use as evidence that outcomes are being manipulated to favor "on the bubble" wrestlers.