An psych experiment on the OOT crowd....

[CallMeIshmael]

This shouldnt take too long at all, and the results might be fun.


The experiment:

Take a coin. Flip it. If its:

Heads: take 10 coins. Throw them on the ground. Now WITHOUT LOOKING AT THEM (very important... just close your eyes) order them on the floor, so they are clearly 1-10. Now, write down, in order, whether it was heads or tails.

Repeat 3 times.

You should now have something like: HTTHHTH.... For 40 coin flips.



Tails: Do not flip a coin. Do your best to make me believe you did though, and make up a string of 40 T/Hs.


Post your results.

I will then try to guess which you did.

(If you have heard about this before, please do not participate)

[poker-penguin]

H T H H T H H T H T

[CallMeIshmael]

[ QUOTE ]
H T H H T H H T H T

[/ QUOTE ]

Gotta have 40 of them. (repeat 3 times)

[mason55]

HHTTHHTTHTTTTHHHHTTHHHHTTHHTTHHHHHHHHHHH

[New001]

HHHHTHTTHHHTHTTTTTTTTTHHHHHTTHTHTTHTHHTT

[istewart]

HHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHH

[gumpzilla]

HTTHHTHTHH
HHHTTTHTHH
TTHTHTTHTT
HTHHTHTTTH

[tbach24]

TTHTHHTHTT
TTHHTTHHTH
HHHTHTTTTH
HTHHHHHTHH

[bump]

TTTHHHTTHT
HTTHTHTHHH
THHHTHHTHT
HTTTHTTTHH

[CallMeIshmael]

[ QUOTE ]
HHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHHH

[/ QUOTE ]

Dis. Qual. I. Fied.

[TStoneMBD]

TTTTHTHHTH
THTHTHHTTH
THHHTTTHHT
HHHHHHTHHH

[daryn]

HHTTHTTHHTHTTHTHTTHTHTHHHTHTTTTHTHHTHTTH

[Soul Daddy]

TTHTTTHTHTHHHTTHTHTTHTHTTTHHTHTHHTHHHTTH

[tbach24]

Isn't it just as likely as any other combination though?

[bump]

[ QUOTE ]
Isn't it just as likely as any other combination though?

[/ QUOTE ]

Oh, Cornell kid got schooled by the highschooler.

[DougOzzzz]

HTHTTHHHTTHTHHHTHHHHTTTHTHHHHHTHHTTTHHTH

[Stuey]

HTTHTHHTHTTTTHTHHHTHTHTTHTHTTHTHHTHHTTHTTHH

[mason55]

[ QUOTE ]
Isn't it just as likely as any other combination though?

[/ QUOTE ]

In fact, why would you make that up? It would be obvious it was made up thus it must be real.

Level 2 thinking baby.

[New001]

Any other 41 coin combination, sure.

[Klepton]

HHHTHTTHTH
THHTHTHTHT
TTHHTHTHTH
HTHHTHTTTH

real or fake bitch

[gumpzilla]

[ QUOTE ]
Isn't it just as likely as any other combination though?

[/ QUOTE ]

I realize you're joking, but . . .

To be produced by chance: yes

To be produced by a human: no, it's far, far more likely than most combinations to be produced by a human.

Insert some Sklanskyism about Bayes' Theorem here. The person who pointed out that there were 41 H's also has a good point.

[cab4656]

TTTHTTTHTTHHTHTTHTTHTHHHTTTTTHHTHTTHTHTT

[Justin A]

H H H T T H T H T T
H T H T T T H T H T
H H T T H T T T T H
T H T H H T H T T H

[Ulysses]

HTHHHTHTTHHHHTHTTHTHHHHHTHTTHHTHTTHTHTTT

[cnfuzzd]

go [censored] yourself. I mean that in the nicest way possible, but if you think theres any chance im doing this, you are freaking crazy.

peace

john nickle

[DBowling]

tthhthtttt
htthththth
hthhhhthht
ththhthtth

[YourFoxyGrandma]

The presentation gives it away, I think.

For example:
HTTHHHHTTHTHTHTHHTHTTTTTHTHTTTTTTHHHTHTH, fake.

HTTHHHHTTH
THTHTHHTHT
TTTTTHTHTH
HTTHTHTHHH, real.

[Ulysses]

[ QUOTE ]
The presentation gives it away, I think.

[/ QUOTE ]

FWIW, I typed mine out as four lines, then removed the linebreaks before posting. I suspect others did the same.

[bholdr]

hhtthhthhh
thhhtthhtt
htthhhhhht
hthhhtthtt

[daryn]

this one is sooooooooo fake

[TStoneMBD]

i dont think it matters, because i originally typed it all out as a one-line, then i went back and editted it for 4 lines to make it easier for cornell to read.

[Thythe]

[ QUOTE ]
this one is sooooooooo fake

[/ QUOTE ]

My guess is like 80% at least are fake considering the non fake way requires a lot more work.

[wacki]

http://www.amazon.com/exec/obidos/tg/detail/-/0393970833/103-9318521-5903838?v=glance

Cornell has officially gone down the shiter. Either that, or this "psych" experiment is over my head.

[tbach24]

[ QUOTE ]
This shouldnt take too long at all

[/ QUOTE ]

2:06 later and I could've watched a marathon, thanks a lot.

[Nottom]

HTHTTHHHHT,TTHTHHTHTT,HTHHTHTTHT,HTTHTHTHHT

[daryn]

</font><blockquote><font class="small">In risposta di:</font><hr />
</font><blockquote><font class="small">In risposta di:</font><hr />
this one is sooooooooo fake

[/ QUOTE ]

My guess is like 80% at least are fake considering the non fake way requires a lot more work.

[/ QUOTE ]

i was joking, but yes, i have already thought of what you just said.

[bholdr]

this is kind of dumb.

[tbach24]

[ QUOTE ]
[ QUOTE ]
This shouldnt take too long at all

[/ QUOTE ]

2:06 later and I could've watched a marathon, thanks a lot.

[/ QUOTE ]

3:01 now, where the hell are you?

[Soul Daddy]

[ QUOTE ]
[ QUOTE ]
[ QUOTE ]
This shouldnt take too long at all

[/ QUOTE ]

2:06 later and I could've watched a marathon, thanks a lot.

[/ QUOTE ]

3:01 now, where the hell are you?

[/ QUOTE ]
The experiment was apparently how many could be duped into posting something.

[lorinda]

HHHTHHTTT rolled under sofa, TTHHTTTTT, HHHTTHTH rolled under TV, THTTTHHT.

Lori

[daryn]

</font><blockquote><font class="small">In risposta di:</font><hr />
</font><blockquote><font class="small">In risposta di:</font><hr />
</font><blockquote><font class="small">In risposta di:</font><hr />
This shouldnt take too long at all

[/ QUOTE ]

2:06 later and I could've watched a marathon, thanks a lot.

[/ QUOTE ]

3:01 now, where the hell are you?

[/ QUOTE ]

wtf are you talking about? stfu and let the "experiment" play out. go to bed and check it tomorrow.

[CallMeIshmael]

[ QUOTE ]
wtf are you talking about? stfu and let the "experiment" play out. go to bed and check it tomorrow.

[/ QUOTE ]

Exactly.


Just because you have finished your post, doesnt mean others who might be willing to participate have yet.


I will post my guesses later tonight.

Also... bump.

[jakethebake]

I'm pretty sure that if you just guess the person didn't even flip the coin the first time and made up the whole thing, you'd be right on about 99% of these.

[namknils]

T T T H T H H T H H
T H T H H T H T T T
H T H T T H H H T H
T H T H H H T H H T

[PokerBob]

nerd

[spamuell]

THHHTHTTTT
TTTTHTHHHT
HTHTTTTHHH
HHHHHHTTHT

[CallMeIshmael]

[ QUOTE ]
The less a man makes declarative statements the less apt he is to look foolish in retrospect

[/ QUOTE ]

[jakethebake]

[ QUOTE ]
[ QUOTE ]
The less a man makes declarative statements the less apt he is to look foolish in retrospect

[/ QUOTE ]

The less a man makes declarative statements, the less likely he is to be right in retrospect either... Do you really think all the people above really flipped the coins?


[/ QUOTE ]

[CallMeIshmael]

[ QUOTE ]
[ QUOTE ]
The less a man makes declarative statements the less apt he is to look foolish in retrospect


[/ QUOTE ]

[/ QUOTE ]

[jakethebake]

[ QUOTE ]
The less a man makes declarative statements the less apt he is to look foolish in retrospect


[/ QUOTE ]

Wow! What a zinger!

Are you going to answer the question?

[OtisTheMarsupial]

Which is which?

ththhtttht
hthhththhh
ththththtt
hhthhththh

thhthtthtt
hthhththth
thhhthttht
hththtthhh

[spamuell]

[ QUOTE ]
Which is which?

ththhtttht
hthhththhh
ththththtt
hhthhththh

thhthtthtt
hthhththth
thhhthttht
hththtthhh

[/ QUOTE ]

The first is the fake.

[Senor Cardgage]

I don't have enough coins handy to do this, and I don't really feel like searching them out. I'm curious about what the actual experiment is, though.

[tbach24]

[ QUOTE ]
I don't have enough coins handy to do this, and I don't really feel like searching them out. I'm curious about what the actual experiment is, though.

[/ QUOTE ]

If you have a graphing calculator handy that would work.

[CallMeIshmael]

[ QUOTE ]
I don't have enough coins handy to do this, and I don't really feel like searching them out. I'm curious about what the actual experiment is, though.

[/ QUOTE ]

I'll probably bump it once more later tonight for the after work on the east coast crowd that might not have seen it yet, then post the results at like 8pm eastern or so.

[Alobar]

[ QUOTE ]


Throw them on the ground. Now WITHOUT LOOKING AT THEM (very important... just close your eyes) order them on the floor, so they are clearly 1-10. Now, write down, in order, whether it was heads or tails.


[/ QUOTE ]

guess I'm going to have to go lowr my brains score in rate myself thread, cuz I dont get this.

Why is not looking at them very important? If I never look at them, its the same thing as making them up in the other option, except this time I threw pennies on floor.

If Im not looking them only when I put them in order, thats just dumb because me being able to see weather they are heads or tails isnt going to influence the order I put them in anyway, because everyone is just going to go typically from left to right. And if they dont, its not like most people have the photographic brain ability of closing their eyes, remember the exact position of 10 pennies littering the floor, putting them in order in a non sequential (left to right, top to bottom, etc) patten, then opening their eyes and remebering the pattern order in their brain and writting down the results.

I must just be missing something and am completely dumb

I am smart enough to realize that a test like this over the internet is pretty pointless because no way did even 15% of you take the time to drag out 10 coins (I dont even keep pennies) and then spend the time throwing them on the ground and writting down the results.

But like every single psych experiment, this prolly has nothing at all to do with the stated purpouse of trying to deduce which is random and which is man made random. Psych experiments are tricky like that.

[CallMeIshmael]

[ QUOTE ]
Why is not looking at them very important? If I never look at them, its the same thing as making them up in the other option, except this time I threw pennies on floor.

If Im not looking them only when I put them in order, thats just dumb because me being able to see weather they are heads or tails isnt going to influence the order I put them in anyway, because everyone is just going to go typically from left to right. And if they dont, its not like most people have the photographic brain ability of closing their eyes, remember the exact position of 10 pennies littering the floor, putting them in order in a non sequential (left to right, top to bottom, etc) patten, then opening their eyes and remebering the pattern order in their brain and writting down the results.

[/ QUOTE ]

basically, the heads people are trying to simulate flipping a coin 40 times.

To do it more quickly, I just said flip ten at a time.

And yes, I do agree that it is VERY unlikely that there is a bias when they have their eyes open, but, having them closed removes all doubt, which is what you want in an experiment like this.

[jakethebake]

I think the whole thing was a trick to see how many ootiots he could make crawl around on the fllor with their eyes closed feeling for coins.

[CallMeIshmael]

Honestly dude, please stop posting in this thread for like the next 5 hours.

I cant see any reason your comments could have biased the experiment, but at the same time, I'd rather not risk it.

[tbach24]

[ QUOTE ]
An psych experiment on the OOT

[/ QUOTE ]

One more nitty thing from me in this thread. lol, I'm such a bastard. Or is this correct?

[wacki]

[ QUOTE ]
http://www.amazon.com/exec/obidos/tg/detail/-/0393970833/103-9318521-5903838?v=glance

Cornell has officially gone down the shiter. Either that, or this "psych" experiment is over my head.

[/ QUOTE ]


[censored] I take this back. I was very tired last night. This is actually a legit (and very cool) experiment. We talked about this in bioinformatics class to prove a very important point.

[jakethebake]

[ QUOTE ]
The less a man makes declarative statements the less apt he is to look foolish in retrospect.

[/ QUOTE ]

[CallMeIshmael]

[ QUOTE ]
One more nitty thing from me in this thread. lol, I'm such a bastard. Or is this correct?

[/ QUOTE ]

No, that was my mistake.

The original title was: An interesting psych experiment..


But... then I was reminded of the time that Rob Corrdory (SP?) ripped on this person for using that word in a clearly uninteresting manner. /images/graemlins/blush.gif

[CallMeIshmael]

[ QUOTE ]
[censored] I take this back. I was very tired last night. This is actually a legit (and very cool) experiment. We talked about this in bioinformatics class to prove a very important point.

[/ QUOTE ]

Ahh...


To be honest, I was surprised by your comment last night. From my limited stay here at OOT, you seem like perhaps THE most likely person to realize what I am doing cannot be found in a stats book.

[wacki]

[ QUOTE ]

To be honest, I was surprised by your comment last night. From my limited stay here at OOT, you seem like perhaps THE most likely person to realize what I am doing cannot be found in a stats book.

[/ QUOTE ]

Yes, it can. I will explain later as I don't want to ruin your experiment.

BTW, I misread your post last night that's why I said what I said. Guiness helped (little bit) in that one too. I feel like an ass now. Please forgive me.

[Slow Play Ray]

okay why not:

THTHHHTTHH
HHHTHHHTHT
HHHHHTTHHT
HTTTHHTHTT

well, what is it?!

[junkmail3]

HTTHHHHTTH
THTHTHHTHT
TTTTTHTHTH
HTTHTHTHHH

[ZeeJustin]

[ QUOTE ]
H H H T T H T H T T
H T H T T T H T H T
H H T T H T T T T H
T H T H H T H T T H

[/ QUOTE ]

Do you know how unlikely it is for this exact combination to come up?? The odds are 1.1 trillion to 1 against this actually ocurring. And you actually expected us to believe this was random? HAH!

[jakethebake]

[ QUOTE ]
[ QUOTE ]
H H H T T H T H T T
H T H T T T H T H T
H H T T H T T T T H
T H T H H T H T T H

[/ QUOTE ]

Do you know how unlikely it is for this exact combination to come up?? The odds are 1.1 trillion to 1 against this actually ocurring. And you actually expected us to believe this was random? HAH!

[/ QUOTE ]

Brilliant!

[wacki]

He's not that far off. If this was done in person, I'd be more than happy to set up a little wager with stakes up to $2,000. Of course my sample set would be a little larger then his.

[jakethebake]

[ QUOTE ]
He's not that far off. If this was done in person, I'd be more than happy to set up a little wager with stakes up to $2,000. Of course my sample set would be a little larger then his.

[/ QUOTE ]

What are you talking about? /images/graemlins/confused.gif

[Dr. Strangelove]

tttthhthtt
hthhhhtthh
tthttthhhh
thhtthhthh

[wacki]

[ QUOTE ]
[ QUOTE ]
He's not that far off. If this was done in person, I'd be more than happy to set up a little wager with stakes up to $2,000. Of course my sample set would be a little larger then his.

[/ QUOTE ]

What are you talking about? /images/graemlins/confused.gif

[/ QUOTE ]

I'm saying that I'm willing to bet $2,000 that if you flipped a series of coins and wrote them down on one sheet and then randomly picked H or T and wrote it down on another sheet I could figure out which one was which. Of course, I would need much more than 40 flips to wager $2K but this could be done in one hour very easily. To be honest, as long as you don't have a cheat sheet of a random sample, you're pretty much screwed.

[jakethebake]

[ QUOTE ]
I'm saying that I'm willing to bet $2,000 that if you flipped a series of coins and wrote them down on one sheet and then randomly picked H or T and wrote it down on another sheet I could figure out which one was which. Of course, I would need much more than 40 flips to wager $2K but this could be done in one hour very easily. To be honest, as long as you don't have a cheat sheet of a random sample, you're pretty much screwed.

[/ QUOTE ]

You said, "He's not that far off." I thought he was waiting until after the night crowd or something before he was even going to start compiling his guesses. I'm lost. /images/graemlins/confused.gif

[Thythe]

[ QUOTE ]
[ QUOTE ]
[ QUOTE ]
He's not that far off. If this was done in person, I'd be more than happy to set up a little wager with stakes up to $2,000. Of course my sample set would be a little larger then his.

[/ QUOTE ]

What are you talking about? /images/graemlins/confused.gif

[/ QUOTE ]

I'm saying that I'm willing to bet $2,000 that if you flipped a series of coins and wrote them down on one sheet and then randomly picked H or T and wrote it down on another sheet I could figure out which one was which. Of course, I would need much more than 40 flips to wager $2K but this could be done in one hour very easily. To be honest, as long as you don't have a cheat sheet of a random sample, you're pretty much screwed.

[/ QUOTE ]

Being a stats and probability major, I would agree.

EDIT: Upon further thinking, I could beat you at this game. I assume you're giving odds as otherwise you're getting free information. Let's say you wager $2K and if you're right you get $2K but if you're wrong I get $2001. I can make this game +EV for myself without a cheat sheet.

EDIT2: My above edit is stupid, as I guess I'd have a cheat sheet in some sense.

[iMsoLucky0]

I want to play. Can someone loan me 2.50?

[Alobar]

you do realize this isnt going to end up being about odds and statistics right?

[DMBFan23]

I think it's more about the psychology of what we think is random and how what we would arrange so as to appear random is in fact more structured in certain ways than actual random occurrences.

[CallMeIshmael]

[ QUOTE ]
you do realize this isnt going to end up being about odds and statistics right?

[/ QUOTE ]

Im hesitant to comment on anything for fear of biasing the last pieces of data, but, I think I can safely say that this is surely not the case.

[CallMeIshmael]

[ QUOTE ]
I think it's more about the psychology of what we think is random and how what we would arrange so as to appear random is in fact more structured in certain ways than actual random occurrences.

[/ QUOTE ]

AHH... Kevin!

Well... since I fear this may scew the results, I will tally it up and post now.

No new data accepted.

[wacki]

[ QUOTE ]
I could beat you at this game.

[/ QUOTE ]

I think you are looking at this only at one level. Think iteratively and think large sample set. Hit a keyboard's T or H key until you get to 2,000. This could be done in an hour easy, but my time limit would be one hour. Even with a 6 hour time limit I would be amazed if you could beat me with any regularity.

[gumpzilla]

[ QUOTE ]
[ QUOTE ]
I think it's more about the psychology of what we think is random and how what we would arrange so as to appear random is in fact more structured in certain ways than actual random occurrences.

[/ QUOTE ]

AHH... Kevin!

[/ QUOTE ]

I hate to rain on your parade, but don't you think that this was blazingly obvious from the getgo?

[CallMeIshmael]

Now that the data train is closed...

Do you really think you're the only person who saw this VERY OBVIOUS bias?

[ QUOTE ]
Do you really think all the people above really flipped the coins?

[/ QUOTE ]

No.. of course not.

[jakethebake]

[ QUOTE ]
you do realize this isnt going to end up being about odds and statistics right?

[/ QUOTE ]

Was this directed at me? Or at statboy-Thythe that's going to beat it? I don't know what system they're using on this thing. I'm not sure how i got dragged into any of this?...LOL.

[CallMeIshmael]

[ QUOTE ]
but don't you think that this was blazingly obvious from the getgo?

[/ QUOTE ]

Judging my the PMs I received for help on figuring it out... no.

Or at least a good chunk of them didnt see it.

(also... do you think this biases the results? Im curious myself on that one. Because its one thing to know its test of our ability to produce random strings, but another to adjust your string such that it appears random/non-random depending on their motive)

[Thythe]

[ QUOTE ]
[ QUOTE ]
I could beat you at this game.

[/ QUOTE ]

I think you are looking at this only at one level. Think iteratively and think large sample set. Hit a keyboard's T or H key until you get to 2,000. This could be done in an hour easy, but my time limit would be one hour. Even with a 6 hour time limit I would be amazed if you could beat me with any regularity.

[/ QUOTE ]

Yeah, as per my second edit, the way I'd win was rather trivial and it somewhat uses a cheat sheet. After flipping the coins, I'd know the results, and would just switch every H or T. If the coins came down TTHHTHHT or whatever, I'd just write down HHTTHTTH giving myself a 50/50 shot. At better than 1:1 odds, it'd be +EV.

[jakethebake]

[ QUOTE ]
I hate to rain on your parade, but don't you think that this was blazingly obvious from the getgo?

[/ QUOTE ]

I thought so. I'm somewhat curious to see what exactly the giveaways are. But, yes, this much was obvious. I'm not sure whay this is a giveaway.

[jakethebake]

[ QUOTE ]
[ QUOTE ]
but don't you think that this was blazingly obvious from the getgo?

[/ QUOTE ]

Judging my the PMs I received for help on figuring it out... no.

[/ QUOTE ]

That's weird because it didn't occur to me that it was anything else. What else would it be?

[gumpzilla]

[ QUOTE ]

(also... do you think this biases the results? Im curious myself on that one. Because its one thing to know its test of our ability to produce random strings, but another to adjust your string such that it appears random/non-random depending on their motive)

[/ QUOTE ]

No, I doubt it matters. Making strings that are going to have the statistical hallmarks of randomness will be very hard. For one thing, people are typically going to try and avoid long strings of heads or tails because it doesn't look random. But it's kind of a giveaway if you don't see a couple of reasonably long strings of the same type. There are other regularities which will be far more subtle, I'm sure.

[CallMeIshmael]

[ QUOTE ]
That's weird because it didn't occur to me that it was anything else. What else would it be?

[/ QUOTE ]

I should edit my post, because it wasnt clear.

I meant, more along the lines, they dont know WHICH statistic about a string is a giveaway.

[Slow Play Ray]

are you done yet?

[RacersEdge]

I would bet that many people with no statistical background would think that

HTHTHTHTHT

was a fairly random.

[Supersetoy]

[ QUOTE ]
This shouldnt take too long at all, and the results might be fun.


The experiment:

Take a coin. Flip it. If its:

Heads: take 10 coins. Throw them on the ground. Now WITHOUT LOOKING AT THEM (very important... just close your eyes) order them on the floor, so they are clearly 1-10. Now, write down, in order, whether it was heads or tails.

Repeat 3 times.

You should now have something like: HTTHHTH.... For 40 coin flips.



Tails: Do not flip a coin. Do your best to make me believe you did though, and make up a string of 40 T/Hs.


Post your results.

I will then try to guess which you did.

(If you have heard about this before, please do not participate)

[/ QUOTE ]

Either way, we're making you believe that we did it/did not do it because we can't look at the coins in the first example. How can a person tell if a coin is heads or tails if he can't look at it? Either way (throwing 10 coins 4 times or making them up) they're going to be completely made up.

Therefore, if everyone followed directions you can easily say that everyone's trial is fake.

[CallMeIshmael]

First off, as I mentioned a few posts ago, I am more than aware that a very large % of those who inputed data didnt in fact flip the coin, even the first time.

The purpose of the experiment wasnt to see if I could guess who used a coin and who didnt (sorry, I lied). I was more interested in having the twoplustwo crowd simply try to replicate 40 coin flips. I felt the way it was presented tended to keep your focus away from thinking about what clues might exist in someone's guess.



Human beings are very bad at being random.

If someone trys to put together a random sequence of 40 coin flips, they tend to bias it against the "correct" number sequences of HH or TT. Just because, having "HHHHH" in the middle somehwere doesnt "look" random.

In a truly random sampling of 40 coin flips, you expect to see 19.5 flip sequences. That is, you should see 19.5 TH or HT sequences.

This was what I used to test if the sequences in the thread were random.


Before I post the results, I have to note the followings disqualifications:


Stuey: Too many flips
Lorinda: Not enough floor space
Istewart: Urinating on the table



There were a total of 23 participants. There "flip counts" were:


19 tbach24
19 dholdr
19 dr strangelove
20 dougozzzz
20 slow play ray
21 Tstonembd
17 new001
22 cab4656
16 spamuell
23 bump
23 el diablo
24 gumpzilla
24 junkmail3
25 soul daddy
25 dbowling
26 daryn
26 justin A
26 namknils
12 mason55
27 nottom
28 klepton
29 otisthemarsupial_1
29 otisthemarsupial_2


This is ordered by distance from the expected value of 19.5.





The standard deviation of the true data set is 3.07.



Thus, if you flop a coin 40 times, and repeat 23 times (as was simulated here), we can expect:


66% of the data to fall in the range: 16.43-22.57


39% of the reported strings fall in that range.



We would also expect that:


95% of the data would fall in the range: 13.36 - 25.64


65% of the reported strings fall in that range.



Even humans who have a VERY good understanding of probability/randomness (you would have to assume that the average twoplustwoer is way ahead of the median for this skill) still can't do a great job at simulating 40 coin flips.

As wacki pointed out, this would be even more obvious at higher numbers. (I kept it small to help participation).

He also pointed out in a PM that I could also use the frequencies of other sequences (HHT, HHH...) to collect even more data.



Now... since I dont know how many actually flipped the coins, I cant predict what each person was.

But... if everyone honestly reports what they did, just take the top of the list, and assume they were the true coin flippers.

For example, if 3 people admit they flipped coins, then my guess would be the top 3 in the list. (tbach24, dholdr, and dr strangelove).

I would say there is at least a decent chance I made a mistake in here somehwere. Either in math or logic. Flame on!


Thanks for the participation, btw.

EDIT: (FWIW, it was the thread about picking your set of skills taht you are #1 at, in which someone said "picking random numbers" that made me do this)

[CallMeIshmael]

[ QUOTE ]
Either way, we're making you believe that we did it/did not do it because we can't look at the coins in the first example. How can a person tell if a coin is heads or tails if he can't look at it? Either way (throwing 10 coins 4 times or making them up) they're going to be completely made up.

Therefore, if everyone followed directions you can easily say that everyone's trial is fake.

[/ QUOTE ]


Sorry if that wasnt clear.

I meant: organize them in order with your eyes closed, THEN look at them.

[SpearsBritney]

Neato!

[spamuell]

Interesting.

I was 9th in the list and I did actually flip the coins, I doubt all 8 of those above me did.

Well, I didn't flip 40 coins, I wrote a quick vb app to do it for me, but it should still be random (I used randomize) so it should amount to the same thing.

[Ulysses]

[ QUOTE ]
23 el diablo

[/ QUOTE ]

Fake.

[CallMeIshmael]

[ QUOTE ]
Well, I didn't flip 40 coins, I wrote a quick vb app to do it for me, but it should still be random (I used randomize) so it should amount to the same thing.

[/ QUOTE ]

Yeah, thats as good as it gets for our intents and purposes.

[RacersEdge]

Are you doing what's called a "runs test"?

[MILFChaser]

THTHHTHTTT
TTTHHHTHTT
THTTTHTHTH
HHTTTTTTHH

[CallMeIshmael]

[ QUOTE ]
Are you doing what's called a "runs test"?

[/ QUOTE ]

I just looked up what that meant. And yes, it appears I did. /images/graemlins/smile.gif

[tbach24]

[ QUOTE ]
19 tbach24

[/ QUOTE ]

[ QUOTE ]
For example, if 3 people admit they flipped coins, then my guess would be the top 3 in the list. (tbach24, dholdr, and dr strangelove).

[/ QUOTE ]

I was tails originally. I'm the man. I would like to think my graphing calculator for assiting me in my one and only flip, and for being there to participate had the original been heads.

[Slow Play Ray]

[ QUOTE ]
20 slow play ray

[/ QUOTE ]

i really flipped (well, i shook up and "rolled" a handful of quarters like dice on my desk calendar 4 times). a perfect random sampling. /images/graemlins/cool.gif

[mason55]

[ QUOTE ]
12 mason55

[/ QUOTE ]

Real.

My last toss of 10 coins all came up heads which really effed things up.

I'm an outlier baby!

[CallMeIshmael]

[ QUOTE ]
Real.

My last toss of 10 coins all came up heads which really effed things up.

I'm an outlier baby!

[/ QUOTE ]

WOW did that one look fake.

[mason55]

[ QUOTE ]
[ QUOTE ]
Real.

My last toss of 10 coins all came up heads which really effed things up.

I'm an outlier baby!

[/ QUOTE ]

WOW did that one look fake.

[/ QUOTE ]

Yeah I opened my eyes and thought "Man, why couldn't I have hit these odds on a horse race instead of a stupid quarter toss"

[wacki]

[ QUOTE ]
[ QUOTE ]
Real.

My last toss of 10 coins all came up heads which really effed things up.

I'm an outlier baby!

[/ QUOTE ]

WOW did that one look fake.

[/ QUOTE ]

Did you let the coins hit the ground??? If you catch a coin it is NOT random.

[TStoneMBD]

yah i actually flipped the coins, and im in the top category

[spamuell]

[ QUOTE ]
If you catch a coin it is NOT random.

[/ QUOTE ]

What? Why?

[bump]

[ QUOTE ]
23 bump

[/ QUOTE ]

fake, never flipped

[DougOzzzz]

[ QUOTE ]

20 dougozzzz


[/ QUOTE ]

Random number generator.

[jstnrgrs]

HTTHHHHTTHTHHTHHHTHTTTHHTHTHTHHHTTTHTHTH

[Sponger15SB]

[ QUOTE ]

Did you let the coins hit the ground??? If you catch a coin it is NOT random.

[/ QUOTE ]

??????????????
??????????????????????????
??????????????????
?????????
??????????????????

[DougOzzzz]

[ QUOTE ]
For example, if 3 people admit they flipped coins, then my guess would be the top 3 in the list. (tbach24, dholdr, and dr strangelove).



[/ QUOTE ]
by the way, last i checked 20 was the same distance from 19.5 that 19 is....
[ QUOTE ]


EDIT: (FWIW, it was the thread about picking your set of skills taht you are #1 at, in which someone said "picking random numbers" that made me do this)

[/ QUOTE ]

And I was the one that pointed out that it is not really such an easy thing to do.

By the way, given a sufficiently large sample size (maybe &gt;1 million), I think that even the lists made by random number generators could be spotted from those made using a "fair" coin. I've done tests on this, and I get some pretty strange results. i.e. 80% of flips after 7 consecutive "heads" result in another heads (over 1000 flips) and things of that sort.

[CallMeIshmael]

[ QUOTE ]
by the way, last i checked 20 was the same distance from 19.5 that 19 is....

[/ QUOTE ]

A) Yes, but if I put you ahead of them, they could say the same thing, right? /images/graemlins/tongue.gif

B) No... 20 is actually slightly "worse" than 19. Since, for the most part, humans tend to scew it upwards, 19 is actually slightly more likely to be random than 20. (this was the tiebreaker for congruent numbers on opposite sides)

[New001]

[ QUOTE ]
17 new001

[/ QUOTE ]

I can't believe I actually flipped 40 coins, but I did.

[CallMeIshmael]

[ QUOTE ]
I can't believe I actually flipped 40 coins, but I did.

[/ QUOTE ]

Im honestly dumbfounded as to how many people actually flipped coins.

(then again, there might be a bias towards coming forth if you actually did flip them)


EDIT: or created/used a RNG

[CallMeIshmael]

[ QUOTE ]
By the way, given a sufficiently large sample size (maybe &gt;1 million), I think that even the lists made by random number generators could be spotted from those made using a "fair" coin. I've done tests on this, and I get some pretty strange results. i.e. 80% of flips after 7 consecutive "heads" result in another heads (over 1000 flips) and things of that sort.

[/ QUOTE ]

What language?


I used C++ to test some things, and afer a million was basically dead on in flipness.

[tbach24]

[ QUOTE ]
[ QUOTE ]
I can't believe I actually flipped 40 coins, but I did.

[/ QUOTE ]

Im honestly dumbfounded as to how many people actually flipped coins.

(then again, there might be a bias towards coming forth if you actually did flip them)


EDIT: or created/used a RNG

[/ QUOTE ]

It would've taken me literally 5 seconds to do 40 samples on my calc, how does that dumfound you?

[pshreck]

[ QUOTE ]


Im honestly dumbfounded as to how many people actually flipped coins.



[/ QUOTE ]

I would estimate their is a 50/50 chance of people who now claimed to have flipped the coins are telling the truth. Surely your testing would account for this. If someone didn't actually flip but posted in the firstplace, we already know they were being dishonest. The fact that you are asking them now whether or not they actually did it, even after explaining thats the point of the test, doesnt mean most, or even a few, will now tell the truth.

[CallMeIshmael]

[ QUOTE ]
It would've taken me literally 5 seconds to do 40 samples on my calc, how does that dumfound you?

[/ QUOTE ]

Most people arent you? /images/graemlins/tongue.gif

[tbach24]

[ QUOTE ]
[ QUOTE ]
It would've taken me literally 5 seconds to do 40 samples on my calc, how does that dumfound you?

[/ QUOTE ]

Most people arent you? /images/graemlins/tongue.gif

[/ QUOTE ]

True, but I suspect that a large majority of OOTiots are smarter and have better logic skills than me. This should've been obvious to most (who have these calcs anyways).

[CallMeIshmael]

[ QUOTE ]
I would estimate their is a 50/50 chance of people who now claimed to have flipped the coins are telling the truth. Surely your testing would account for this. If someone didn't actually flip but posted in the firstplace, we already know they were being dishonest. The fact that you are asking them now whether or not they actually did it, even after explaining thats the point of the test, doesnt mean most, or even a few, will now tell the truth.

[/ QUOTE ]

I was thinking about this, but I dont know if its quite that strong. Though I do agree that I cannot assume that everyone who came back and said I flipped the coins, actually did.

Simply because I feel people would tend to lie quite a bit less in the second situation. Partly because the "trick" part of the experiment is over. Also, because I sort of stated that lying was OK in the first part, when I asked them to fool me.

(though someone may wish to fool me by saying "I flipped" when they didnt and scored well away from 19.5 (or vice versa), I didnt really care that much about the predictions part, I just wanted to see the data)

[CallMeIshmael]

[ QUOTE ]
True, but I suspect that a large majority of OOTiots are smarter and have better logic skills than me. This should've been obvious to most (who have these calcs anyways).

[/ QUOTE ]

I think you might over estimate the % of OOTers who have access to a RNG, be it through a Graphing Calc, or programming skills. (also, they have to know how to use the RNG on their calc... I have one, and dont know this off hand, and I sure as hell wouldnt look it up for some punk poster)

Though I could be WAY OFF on this one, because this is a pretty eclectic group.

[daryn]

please mention that you own a graphing calculator again. please.

[tbach24]

[ QUOTE ]
please mention that you own a graphing calculator again. please.

[/ QUOTE ]

I actually don't. I got lent one by the school cuz some faggot at my correctional school stole and broke mine and I couldn't prove it past that I saw him do it.

[NoTalent]

thhtthhthh
hhhhtttthh
thhttthhht
ttthhhhtth

[DougOzzzz]

[ QUOTE ]
[ QUOTE ]
By the way, given a sufficiently large sample size (maybe &gt;1 million), I think that even the lists made by random number generators could be spotted from those made using a "fair" coin. I've done tests on this, and I get some pretty strange results. i.e. 80% of flips after 7 consecutive "heads" result in another heads (over 1000 flips) and things of that sort.

[/ QUOTE ]

What language?


I used C++ to test some things, and afer a million was basically dead on in flipness.

[/ QUOTE ]

I tested this in Excel using VBA - just tried it again, with 20,000,000 flips.

Heads came up 49.999 % of the time, there were 9,993,914 "runs", vs. an expected 10,000,001. This is 2.72 standard deviations away from the expected runs. It's not way off, certainly better than any human could do.

However, it's the distribution of the "runs" that makes it really odd. There were 0, absolutely NO streaks above 10 or greater for either heads or tails. There should have been nearly 10,000 of these streaks.

There were 225,000 streaks of EXACTLY 6 heads or EXACTLY 6 tails - vs. an expected 156,000.

After flipping 5 heads in a row, the chance of a 6th heads was 61.96%. After the 6th head, the chance was just 40.35%. After the 7th, 43.23%. After the 8th, 7.7% (not a typo, 2174/32321).

The results for heads and tails were almost identical, with the same odd patterns. So clearly something is wrong with VBA's RNG.

[CallMeIshmael]

Wow that is odd.


I'll run the same tests tomorrow, and see what I come up with.

[daryn]

</font><blockquote><font class="small">In risposta di:</font><hr />
</font><blockquote><font class="small">In risposta di:</font><hr />
please mention that you own a graphing calculator again. please.

[/ QUOTE ]

I actually don't. I got lent one by the school cuz some faggot at my correctional school stole and broke mine and I couldn't prove it past that I saw him do it.

[/ QUOTE ]

i am beginning to view you and dead as essentially the same person

[Vince Young]

Every single combination posted so far has been fake.

[CallMeIshmael]

[ QUOTE ]
Every single combination posted so far has been fake.

[/ QUOTE ]

I'll bite...


And what makes you say this?

[Vince Young]

Because no one's going to do this:
[ QUOTE ]
Take a coin. Flip it. If its:

Heads: take 10 coins. Throw them on the ground. Now WITHOUT LOOKING AT THEM (very important... just close your eyes) order them on the floor, so they are clearly 1-10. Now, write down, in order, whether it was heads or tails.

Repeat 3 times.

[/ QUOTE ]

[CallMeIshmael]

[ QUOTE ]
Because no one's going to do this:
[ QUOTE ]
Take a coin. Flip it. If its:

Heads: take 10 coins. Throw them on the ground. Now WITHOUT LOOKING AT THEM (very important... just close your eyes) order them on the floor, so they are clearly 1-10. Now, write down, in order, whether it was heads or tails.

Repeat 3 times.

[/ QUOTE ]

[/ QUOTE ]

OK... I will say this as nicely as possible...

You (despite what bisonbison will tell you) are not a f[/i]ucking snowflake. If its that obvious to you, its probably that obvious to everyone else.

The fact that most people wouldnt do this is COMPLETELY OBVIOUS to someone who is making up the experiment.

The experiment clearly doesnt hinge on the assumption that people are actually doing this.

(FWIW, I've pointed this out about 3 times already)

[kyro]

THHTHHHTTH
THTTHHTTTH
HHHTHHTHHH
HTTHHTTTHT

[OtisTheMarsupial]

my first one was real, second one was fake.

[Soul Daddy]

[ QUOTE ]
Because no one's going to do this:
[ QUOTE ]
Take a coin. Flip it. If its:

Heads: take 10 coins. Throw them on the ground. Now WITHOUT LOOKING AT THEM (very important... just close your eyes) order them on the floor, so they are clearly 1-10. Now, write down, in order, whether it was heads or tails.

Repeat 3 times.

[/ QUOTE ]

[/ QUOTE ]
I was going to do it, why not? But my first flip was tails and I followed the rules. Why would people participate in the experiment just to attempt to randomly generate results?

[Dr. Strangelove]

I used an RNG.

[tbach24]

[ QUOTE ]
[ QUOTE ]
[ QUOTE ]
please mention that you own a graphing calculator again. please.

[/ QUOTE ]

I actually don't. I got lent one by the school cuz some faggot at my correctional school stole and broke mine and I couldn't prove it past that I saw him do it.

[/ QUOTE ]

i am beginning to view you and dead as essentially the same person

[/ QUOTE ]

no. dead is irrational/agressive and i am not.

[DeadIsARetard]

[ QUOTE ]
no. dead is a retard and i am not.

[/ QUOTE ]


fyp

-DiaR

[lorinda]

"Yeah, thats as good as it gets for our intents and purposes. "

It may be a good idea if you repeat this anywhere to link to a coin flipping program somewhere to maximize the odds that people will actually consider moving off their chair.

Edit: I realise that you are saying repeatedly that it doesn't matter, but I think it would also lower the chances that they bother to lie about doing it or not.

Lori

[k000k]

[ QUOTE ]
By the way, given a sufficiently large sample size (maybe &gt;1 million), I think that even the lists made by random number generators could be spotted from those made using a "fair" coin. I've done tests on this, and I get some pretty strange results. i.e. 80% of flips after 7 consecutive "heads" result in another heads (over 1000 flips) and things of that sort.

[/ QUOTE ]

Not true, I did extensive research for 2 semesters in RNG's using many different tests and methods to determine how random data is, including obvious tests like arithmetic mean, and much more sophisticated tests like entropy, chi square distribution, monte carlo pi value, and serial correlation. I personally tested billions of 'random' bits hundreds of times over the year, and what's returned by the C rand() function is indistinguishable from true random data. If it could be determined that C rand() returns non-random values, it'd take a more than trillions of bits to tell.