Update Analysis.md

This commit is contained in:
Nuño Sempere 2018-11-15 13:20:40 +01:00 committed by GitHub
parent b4abd4046d
commit b24238bfe5

View File

@ -106,11 +106,16 @@ For the 35 people who took part in the original prediction making, their results
The average accuracy is 55.12%, that is, the average participant got 13.22 out of 24 questions right. If it had been reached, a target credence of 80% would imply an average of 19.2 correct answers. In other words, in this limited domain, when these people say 80%, the thing happens 55% of the time. If they bet, they'd be replacing ~1:1 bets with 1:4 bets.
## Is this an spurious result because a small number of questions were really, really hard?
No. See the following scatterplot:
![](https://nunosempere.github.io/rat/EA-predictions/Scatterplot-questions.png)
## Further analysis
Questions for further analysis:
1. Should the two savants who got very near 80% be proud, or should we expect them to exist merely by chance?
2. Are the results an artifact of a small number of questions which were really hard (f.ex. the % of LessWrongers in EA)?
1. Should the two savants who got very near 80% be proud, or should we expect them to exist merely by chance? Maybe.
2. Are the results an artifact of a small number of questions which were really hard (f.ex. the % of LessWrongers in EA)? Solved: No, See above.
I expect to answer those questions in the near future.