An observed card is twice as likely under deck R as under deck B. Before observing it, odds R:B are 1:9. Does the…
Quant ResearchLevel: IntermediateEvidence does not decide a hypothesis
An observed card is twice as likely under deck R as under deck B. Before observing it, odds R:B are 1:9. Does the observation make R more probable than B?
Hints
- Work with odds rather than raw probabilities.
- Evidence in favor is not the same as posterior probability above one half.
Answer
No. Posterior odds equal prior odds times likelihood ratio: (1/9)*2=2/9, giving P(R|card)=2/11. The evidence raises R from 1/10 but does not make it the more probable hypothesis.
Source and licence: Lehman, Leighton & Meyer — Mathematics for Computer Science (2018-06-06) · CC-BY-SA-3.0 · answer: Quantoros editorial