Proof of Immortality III

[godless dave]

Dave,
- That seems like you're saying that Bayesian statistics doesn't work...

That's the opposite of what I'm saying.

The application of Bayesian statistics you're claiming to use is based on contrasting the probability of observing an event given one hypothesis is true with the probability of observing the same event given a different hypothesis is true.

P(E|OOFLam) is based on OOFLam being true.

P(E|~OOFLam) is based on OOFLam not being true.

This is the formula you have been using all along.

If you want to use Bayes in a different way (the more familiar form is: P(H|E)=P(E|H)P(H)/P(E) )then knock yourself out. But that's not the formula you started the thread with.

 

[godless dave]

In my limited understanding:

P(H|E) = P(E|H)P(H)/P(E)

The posterior probability - the probability of a hypothesis given the observed evidence - is P(H|E). It's the probability of H given E, after E is observed.

The prior probability - the probability of H before E is observed - is P(H).

The likelihood is the probability of observing E given H, P(E|H).

P(E) is the marginal likelihood, and is the same for all possible hypotheses being considered.

This all comes from the Wikipedia article on Bayesian inference: https://en.wikipedia.org/wiki/Bayesian_inference

To contrast hypotheses, you create a formula for each hypothesis. Nowhere does it say that you use any values from the result of one formula in the other. If H1 is one hypothesis, and H2 is a competing hypothesis, then you compare the results of each formula:

P(H₁|E) = P(E|H₁)P(H₁)/P(E)

P(H₂|E) = P(E|H₂)P(H₂)/P(E)

You don't use the second formula to change the first, and you don't use the first to change the second. There is one formula for each hypothesis, and you compare the results to determine which hypothesis is more probable.

 

[JoeMorgue]

Exactly. We are basing that likelihood on OOFLam being correct.

YOU CAN'T DO THAT!

What part of that don't you understand? You can't base on predictive on an assumption and have it retain any meaning! Literally dozens of individuals over the course of years have explained this to you in ways a child could understand.

You might as well says "If 2 was really equal to 3 would agree that 2+2 equals 6." It's totally meaningless.

We're saying, "IF OOFLam is correct, then..."

No we are not. "You" are the only one saying this nonsense. We're telling you why it's wrong.

 

[zooterkin]

Thread running slowly, continued here.

Posted By: zooterkin