23 Mar 2011, 23:25

G. ADAM wrote:The expected average result for 1 batch of 3 words

is 1 word right, same as with replacement.

ABC 3 right

ACB 1

BAC 1

BCA 0

CAB 0

CBA 1

6 trials with each sequence showing up once only = 6 hits

You are using the expected result in a very strange way. The only way you can beat your expected average is to get 3/3. Don't you see how it is the wrong approach? If you get 1/3 100% of the tme over a large sample, you will have far exceeded the expected results. If you get 0/3 100% of the time over a large sample there will also be something very strange going on. Do you see what I mean?

23 Mar 2011, 23:54

it might be interesting for post analysis and we could define a new metric if something like that happens, which I'm not expecting as the paranormal bias should be evenly distributed for each word guess.

Correct the only way I can pass is to get the OCCASIONAL 3/3 and probably LOTS of 1/3 too.

There are several models to calculate the odds, but monte carlo simulation is quite accurate.

Say for 100:1 odds, 10 batches, you type in 10, 100 SIMULATE

Do that 10 times, write down the 10 high scores.

I got:

BATCHES = 10

SIMULATIONS | ODDS = 100

HIGH SCORES

17

20

18

18

19

18

17

17

18

17

so the middle value is 17 or18

So the pass mark for 10 batches would be 19 words right from 10 batches of 3.

That would prove supernatural with 1 in 100 chance of error!

Let's make 2/3 on average the pass mark for atleast 10 batches!

So you want to set up a 100:1 ODDS test?

Correct the only way I can pass is to get the OCCASIONAL 3/3 and probably LOTS of 1/3 too.

There are several models to calculate the odds, but monte carlo simulation is quite accurate.

Say for 100:1 odds, 10 batches, you type in 10, 100 SIMULATE

Do that 10 times, write down the 10 high scores.

I got:

BATCHES = 10

SIMULATIONS | ODDS = 100

HIGH SCORES

17

20

18

18

19

18

17

17

18

17

so the middle value is 17 or18

So the pass mark for 10 batches would be 19 words right from 10 batches of 3.

That would prove supernatural with 1 in 100 chance of error!

Let's make 2/3 on average the pass mark for atleast 10 batches!

So you want to set up a 100:1 ODDS test?

24 Mar 2011, 16:57

OK, so I take it Arouet doesn't like the idea that if you simulate 1,000,000 psychic tests with random guesses

then if there's a single highest scorer then he roughly broke 1,000,000:1 odds!

How about this proposal.

Just tele-ask me 2 words

One at a time, no options or anything I'll take 5 guesses from the 25 word list.

That's all I ask, if it works then I can get the ex-president of Aus Skeptics to do a demo test.

That's all I need is 2 trial runs!

Yes I know it proves nothing to you but it's proof of concept to me.

You post the numbers for word 1.

I post 5 guesses

You post the word

DAY 2

You post the numbers for word 2

I post 5 guesses

You post the word

G. Adam leaves, good riddance!

DEAL?

then if there's a single highest scorer then he roughly broke 1,000,000:1 odds!

How about this proposal.

Just tele-ask me 2 words

One at a time, no options or anything I'll take 5 guesses from the 25 word list.

That's all I ask, if it works then I can get the ex-president of Aus Skeptics to do a demo test.

That's all I need is 2 trial runs!

Yes I know it proves nothing to you but it's proof of concept to me.

You post the numbers for word 1.

I post 5 guesses

You post the word

DAY 2

You post the numbers for word 2

I post 5 guesses

You post the word

G. Adam leaves, good riddance!

DEAL?