I cannot win on pokerstars. Reasons ??

[Josem]

to respond to your other points:

[ QUOTE ]
1-People say it's impossible to say online poker is rigged. 100% certainty yes. That's your confidence level.... 95% is very good, at least for me.


[/ QUOTE ]
that is just plain wrong. with the right evidence, you could certainly prove that online poker at a particular site is rigged.

"People say it's impossible to say online poker is rigged" - which is true, on the basis of evidence currently available. On the evidence available now, it is impossible to say online poker is rigged.

[ QUOTE ]
2-What about the time series (taking the order of the events into account)? Ex: I toss a coin a 100 times. Get about 50 heads so it's ok, right? What if the fist 40 times I tossed the coin I got heads? NOT right! But the average is still perfect. Think about it! One way to take this into account is to count the distance between the events, lets say, the distance d between AA's (if I get AA and the next hand I get AA d=1). I swear the most probable distance is one! the d distro should be [(1-p)^d]*p. If you plot a histogram (monolog) of d it should be a straight line (y is log(#events on bin) ) for a large sample.

[/ QUOTE ]
We do not have a publicly available analysis of the time series, so it is silly to make conjecture on the basis of a possible distribution.

[ QUOTE ]
2b- People say you need a big sample to say a site is rigged (or suspect with very good reasons). Wrong! Let's say you see 2 or 3 royals on a row. That's only 2 or 3 events

[/ QUOTE ]

But the sample is much higher than you realise.

Of the hundreds of thousands of people who post on this board, they play hundreds of thousands of hands each (I don't know what the average playing experience of people on this board is, but I imagine that those who have played millions of hands compensate for those who have played few).

we're now looking at hundreds of billions of hands - if the person who gets two royal flushes in a row (at odds of x million to 1, or whatever it is) posts about it (as he is likely to) that can not now be proof that online poker is rigged.


[ QUOTE ]
3-Now for less numbers and more feelings: Party poker changed something this week, I feel.

[/ QUOTE ]

At least points 1- 2b were at least credible and showed some logical thought (although they overlooked serious flaws in the thinking process). This is just silly.

A mistake that many people make is to intuitively over-estimate the favouritism that a hand like AK has over 72 (or whatever). That is, incidentally, why in STTs and MTTs hyper aggressive short-stack play is so incredibly important and the key to success - if you pick up the blinds, you get a huge boost, and if you get called, you're rarely worse than 40% chance of winning, and hardly ever worse than 20% chance of winning.

[Josem]

[ QUOTE ]
Ok Josem, if you say so....

But it's still data! Show me the other 99% of AA's that are closer than 2.37 sigma and I will be happy to agree.

[/ QUOTE ]

If sciolist (sp?) posted the results of all 169 hands, i'm confident they'd fit within the expected framework.

[ QUOTE ]
Data
* Rejection of "bad" data on arbitrary grounds, instead of according to previously stated or generally agreed criteria.
* Rejection of "outliers" on statistical grounds that fail to take into account important information that could be derived from wild observations as described by Kruskal.

[/ QUOTE ]

Right... your analysis, which only takes into account the AA, rejects the data for hands 22-KK.

Doesn't this prove the failure of your own analysis? Or are you trying to make some other point here? That quote is exactly what i am trying to say (although they use much more complicated terminology than I have)

I felt I was quite clear in saying that the failure of your analysis was because you focused on only one hand rather than the 13 hands that we have been provided with.

[washus]

Josem, you cannot disprove anything to 100% certainty. If you got 100 royals in the first hundred hands of online poker ever (not the billions you say), that's NOT proof to 100% confidence level, the probability is not zero. You NEED a confidence level.... remember reasonable doubt? The probability that all molecules in the air in your room go to one corner and you asfixiate is NOT zero, just astronomically small.

Don't you have your own (numbered) hands? although it's not derived from the ordered series of the PRNG it's still a time series.

Point 2b: I didn't realize the number was so big. Anyway, just slash 2 or 3 and put 5 or 6 (think thats enough). Still small number of events. Hell, even 3 is big, man!

I will not argue point 3 with you, since I know s**t about poker. I just would like very much if you could check. Just check. Don't play, just go there and look. It's my intuition, thats all. And I agree intuition doesn't mean much.

[Josem]

[ QUOTE ]
Josem, you cannot disprove anything to 100% certainty.

[/ QUOTE ]
Yes you can.

There are some things that are true. Some things are lies.

1 + 1 = 2. That is 100% certain.

[ QUOTE ]
If you got 100 royals in the first hundred hands of online poker ever (not the billions you say), that's NOT proof to 100% confidence level, the probability is not zero.

[/ QUOTE ]
Correct.

[ QUOTE ]
You NEED a confidence level.... remember reasonable doubt? The probability that all molecules in the air in your room go to one corner and you asfixiate is NOT zero, just astronomically small.

[/ QUOTE ]

I agree.

[ QUOTE ]
Don't you have your own (numbered) hands? although it's not derived from the ordered series of the PRNG it's still a time series.

[/ QUOTE ]
I haven't ever looked at the time series distributions on them.

[ QUOTE ]
I will not argue point 3 with you, since I know s**t about poker. I just would like very much if you could check. Just check. Don't play, just go there and look. It's my intuition, thats all. And I agree intuition doesn't mean much.

[/ QUOTE ]

I play on PartyPoker. I haven't noticed anything different this week.

[washus]

Jesus Josem, I didn't reject them, I just took the AAs which was calculated already. Look at the plot man! better pairs tend to be further from the mean.
But the main point of my post is that you guys look at 2.3 sigma as ok!
But for those pairs.... I need other 98 pairs that are lower, not 12!

Please look at your data. I don't care who's right or wrong. This is the first post I saw data. Some of this data was, for me, astonishing, and everyone treated it as normal.

anyway, if your intuition says its not rigged (maybe not even in the sense of fraud, maybe just bad simulation... maybe a bad RNG traded for security) than fine. The data on this thread does not support it. Fluke, maybe. If you bet on it you need 100:1 pot odds from this data.

That's my view. I dont want to argue with noone josem. I just wanted to point out this data is NOT ok, as some people said.

[realjaydub]

[ QUOTE ]
Jesus Josem, I didn't reject them, I just took the AAs which was calculated already. Look at the plot man! better pairs tend to be further from the mean.
But the main point of my post is that you guys look at 2.3 sigma as ok!
But for those pairs.... I need other 98 pairs that are lower, not 12!

Please look at your data. I don't care who's right or wrong. This is the first post I saw data. Some of this data was, for me, astonishing, and everyone treated it as normal.

anyway, if your intuition says its not rigged (maybe not even in the sense of fraud, maybe just bad simulation... maybe a bad RNG traded for security) than fine. The data on this thread does not support it. Fluke, maybe. If you bet on it you need 100:1 pot odds from this data.

That's my view. I dont want to argue with noone josem. I just wanted to point out this data is NOT ok, as some people said.

[/ QUOTE ]

Interesting....

I was leveling everyone on the other thread but wow.

[washus]

1+1=2.... That was cheap, huahuahau. Mathematics doesn't count. There you can prove and disprove things, like P(any pair)=3/51.
We're talking proving a set of data follows a certain distribution.

It's very late around here.... nice talking to you Josem. I'll drop by tomorrow to see new posts. cya

[Josem]

[ QUOTE ]
1+1=2.... That was cheap, huahuahau. Mathematics doesn't count...We're talking proving a set of data follows a certain distribution.

[/ QUOTE ]

The point of 1+1 = 2 was that some things are 100% true. Outside the realm of mathematics, for example, as I write this, there is a 100% chance that I am alive. There is 0% chance that I am dead.

More importantly, it is possible to prove 100% that poker is rigged. One way of doing this would be for someone to confess to rigging it, and providing data providing the point.

Apart from anything else, this is a bit of a diversion from the topic.

[ QUOTE ]
It's very late around here.... nice talking to you Josem. I'll drop by tomorrow to see new posts. cya

[/ QUOTE ]

Sleep well. I don't envisage posting much more unless there's some new material contributed to this thread (you certainly contributed new stuff yourself)

[Bobo Fett]

At some point in this thread it was discovered that OnlinePro was using an outdated version of PT that was not displaying all of his stats correctly. Are you using the figures he initally posted, or the correct numbers that came much later?

[ QUOTE ]
Anyway, someone said "Standard error is 22.4. 555 is 2.37 standard errors from expectation. A deviation that big would occur ~1.8% of the time by chance. A little less often than hitting a one outer on the river. So far, meh."

At least for me, 2.37 sigma is NOT small. That 1.8% (didnt check it for a normal distro) means that ONLY 1.8% of samples of this size (~11k) would be expected to be this far from the mean! That means that 99.2% would NOT be this far.
That means that I would have to see other 99 sets of data as big as OP's to say, ah, ok, OP's was a fluke.

[/ QUOTE ]
I assume you meant 98.2%, but your point remains the same. Here's the thing, though. NONE of us are going to start a thread saying that out stats look completely normal. As a matter of fact, I think there are enough PT-savvy people that study their stats carefully enough that it's fair to say that the number who have examined their stats and not posted them on here BY FAR exceeds 99.

This of course proves nothing...I have no hard numbers to back this up. I just think it's very reasonable to expect a post like OnlinePro's to be a 1% occurence.

[Bobo Fett]

[ QUOTE ]
Interesting....

I was leveling everyone on the other thread but wow.

[/ QUOTE ]
Haha...I didn't think you'd ever come right out and admit it. What will your 2 or 3 supporters do now? I suppose OnlinePro must retake the lead! [img]/images/graemlins/grin.gif[/img]