I'm not a math expert at all, but shouldn't your scatterplot be based on samples similar to the ~3000 hands of nionio? It seems you included samples of "at least 2500" implying that all are larger than that. The reason I'm asking is the only way this isn't an open and shut case of cheating is that 3k hands statistically is so small that it might be possible to run at a very high winrate/loserate simply based on variance. Obviously the more hands nionio logged at a high winrate the less likely it is to be variance. Would it really be accurate to compare a 3k sample to a 30k or 300k sample of hands?

The larger the sample size the less likely it is to see a very high winrate, so comparing his winrate to larger samples would make it look more abnormal than it perhaps is. Anyway this is obviously irrelevant if I misunderstood how you made your graph.

BF,

You make a fair point, although I suspect any such visual effect will be pretty marginal, since those areas are already very dense.

That said, of the 870 plotted points, 710 - the vast majority - are of under 7,000 hands, and 334 are between 2,500 and 3,500 hands.



If we reduce the sample size to the 334 players with 2,500 to 3,500 hands recorded, the mean bb/100 becomes .52 and the standard deviation is 17.12 - leaving the alleged cheater out at almost 9 standard deviations above the mean.

9 standard deviations is something in the order of 1 in 1,000,000,000,000,000,000 - or winning three consecutive 1-in-a-million events.



Of course, if anyone has any hand histories to help improve the sample size, feel free to email them to me at michael@michaeljosem.com


edit:
p.s. i understand that there are another 5k hands with the alleged cheater winning at the same rate. this would suggest that it is reasonable to include all the players that i have data for.

Josem,

That's even luckier than this!

El D,

They would be about on track if they had also won the lottery the following day.

Wow. Nice work josem.

Pretty ridiculous story. They finally win big and it seems like it didn't even happen.

The shown math (if correct) is more of a proof there was cheating going on than any hand history could be.

Sorry to see but I'm wondering since UB=AP and they are so closely connected why guys would ever trust UB. BTW what is up with the hand where he has 2 pair and the guy hits a set on the river. He makes good value bets but checks behind 2 pair? ok whatever but look at the other hands too it's pretty obvious in a non obvious way.

I hope you guys aren't seriously hoping for a smoking gun or ludicrously correct T high calls again because that isn't happening. How can all the best guys on the internet play this guy and yet all agree that something is fishy. Sure he can run good against a number of people but against all the best players here? Seems unlikely and kind of obvious to me and please don't consider the AP cheaters as the standard because if you do I don't think you'll ever find a cheater.

Talk about a selling point, geez.

The only way to convince people "beyond all reasonable doubt" (either to confirm or dispell cheating concerns) requires evidence that UB must hold.

This would include a determination of whether the accounts - or other accounts - had access to the hole cards.

Thus, while I don't think it is possible to prove beyond all reasonable doubt that some cheating took place here, it is:
a) possible
and
b) deserving of further investigation from the KGC and/or UB

nio is not nine in greek ennia is the right.there is no word nio in greek

^^didn't someone say it was "nine" in swedish or something?

Josem, the graph is a good idea but it is extremely misleading, and it would be premature for people to start throwing around numbers like nine or ten standard deviations above the mean.

This scatterplot doesn't mean anything for (at least) two reasons. First, there are few samples with very high VPIPs like NioNio. These will have by far the most widely varying results that are much less likely for the cluster of sane, "normal" players. Second, there's an enormous selection bias at work: if this guy wasn't cheating he was the maniac who got struck by lightning; no one makes threads like this when the crazies lose.

I'm sorry to dump on your graph but drawing meaningful statistical conclusions about this player's luck is very tricky and needs to be done by someone well-versed in this kind of analysis. (I certainly don't feel I have the background to do this.)

My ideas for improving the scatterplot would be as follows.

-First, get every hand possible on NioNio.

-Obtain a (large) sample of data on players with vaguely similar styles, VPIP, aggression, etc. at similar stakes to get an idea of their lossrates and standard deviations. This will give you a poor approximation of the sample pool from which this guy would have been drawn were he not cheating.

-Simulate a bunch of 3k hand random walks using the average maniac lossrate and NioNio's observed standard deviation. These represent NioNios in alternate universes, so to speak.

-Now scatterplot and observe how much of an outlier NioNio is.

Ideally, you would repeat this for a range of lossrates to see how robust the conclusions are. The likelihood of extreme results may be extremely sensitive to small changes in parameters.

This is just a start and I'm sure people with better stat and programming backgrounds would be able to do better.

agree w/ GoG. hopefully as more information becomes available more strenuous analysis will be done

also, ty josem for the efforts you have made and any future work

Gift of Gab,

I recognise that the data is not perfect.

Anyone willing to contribute data is welcome to- I posted my email address in this thread for anyone who wants to contribute.


As a later post of mine said:
a) this graph/statistic does not prove anything beyond a reasonable doubt
b) it seems quite possible for the alleged account to have been cheating
c) the evidence to prove or disprove cheating is held by UB


Of course the graph does not prove anything beyond a reasonable doubt - that is why further investigation is needed, and UB needs to come clean either way.

Hey guys, we need to put all kinds of pressure on UB, Annie Duke, and Phil Hellmuth. We must never stop digging for the truth. The crooks who are stealing our money must be stopped.

We must band together, unite as one. Together we can bring them down.

As others have said, the hands don't really matter. The stats, along with the fact that he stopped playing on the date of the AP scandal, prove it pretty conclusively. That is, if the stats and information are correct.

I think we would all be far less inclined to believe this if there wasn't just such an incident that occured but a few months ago on a site that is affilliated somehow with the one currently in question. I mean, if this happened a year ago I'm sure nobody would think twice and just laugh all this superuser stuff off, but now it's becoming pretty clear that not only is it possible, it's already happened and probably many times. It's crazy to think that a cheater could be so dumb. Like, make a play here or there that makes it obvious he can't see the hole cards. Like value raising two pair into a set on occasion, or making a bad river call. From a profitablity standpoint, it makes sense to give up a few pots here and there and make some intentionally bad plays for the sake of staying under the radar to make more money later on.

The stats for the most part seem convincing, but I also think his W$SF% is a little low for what I'd expect a superuser to have. 50 is extremely high normally, but considering Kotkis has a W$SF of 52-53 in his PT screenshot for 07, I can't help but not feel totally convinced that this guy can see hole cards. I would be extremely suspcious and would avoid playing the higher stakes games on UB until more info gets revealed in the meantime.

Part of me wants to see this guy caught, but another part of me thinks how bad this would reflect on online poker. Two relatively major sites caught in a matter of months? That doesn't look good at all.

NioNio= NineNine in Swedish

I would agree whole heartily with this. The guy could just be a good player?!?!?! Is that so hard to believe? The hands shown as examples are far from convincing..

haha is that suppost to add to the theory?!?! Noting conrete in that!

does kotkis win 60bb/100? I challenge you to find a 8k hand stretch from ANYONE (not doctored obviously) that shows that high a winrate. heck, try finding a winrate like this over 3k hands. he certainly makes calls with the worst hand on the river, but he never turns those made hands into bluffs, in any of the hands we see, and he also checks down some strong hands (for example when he chks down two pair when trambo setted up), or he checks down air when the other player has a pair or greater that he doesn't think he can bluff him off (recall that he tried to bluff piejay off AK on an AKxxx 4 club board when piejay did not have a club (and piejay made a nice call).

do you think the AP thing was "bad" for poker? What about having 700k taken off ub by ONE SINGLE PLAYER in a matter of 3 months, after he decimated ALL, not a few but ALL of his opponents, then magically disappeared. I am more concerned about forcing sites to have integrity in their software, and forcing them to beef up their customer service.


FYI: Last night mrwonkman and blackhole and myself were sitting in the 25/50 game on ub because phil hellmuth was sitting there, and we obviously chatted to him about NIONIO and the strong possibility he was a super user, and he sent an email while we were playing...granted, it means nothing, but we'll see, as a wise man once said: anything is possible, if 50 fked vivica...

FWIW he did not run significantly above expectation in all in pots, as evidenced by the graph trambo posted. He did not "run hot."

If he were such a good player, why wouldn't he continue to decimate the best players on ub, or why wouldn't he try stars or ftp or ipoker? He mysteriously vanishes and stops playing completely on 9/4 after having taken 700k+ (moderate projected win rate) off the site...if he were "that good" wouldn't he want to continue playing? Heck, even if his win rate were cut in half he would still destroy.

How do you know he's not on stars or ftp?? Just cause he changes his username? I have plenty of usernames among the many different poker sites...
People decide to move poker sites all the time...

Fair enough it's suspicious about closing the account, I'm sure there is a story behind it, but for me doesn't give anything concrete to be branding him as a superuser!?

the stats are pretty compelling. i dont think a lot of people are grasping just how significant it is to win at the rate he did over several thousand hands without "getting lucky" in a vast majority of all-in situations. Those types of hands are far and away the easiest way for your short term actual winrate to differ wildly from your long term theoretical winrate. Furthermore, from my experience (good) players that are running hot in the games, by winning more than their equity in all-in situations and by getting setups very rarely win more than 30bb/100 over a few thousand hands. The player in question is winning at more than twice that rate, and without those setups. So, regardless of the hands posted, which I didn't look at, I'm strongly convinced that something very surreptitious took place.

This is very significant and more than negates the valid points GoG is raising. Much of the variance in poker comes from deviations in expected returns on all-ins (big sums of money bet with small edges). Given the virtual absence of this phenomenon, there either has to be a sick amount of setups in showndown hands or you have to be virtually missing every single flop/draw (variance has to come from somewhere!). If not, he's to be making many big bets with almost 100% folding equity in another way in order to achieve this winrate, i.e. he's seeing your holecards.

One more point noone has raised: he's not beating some random spewmonkey; he's literally killing world-class players without getting lucky on all-ins or running into an insane amount of setups. This guy is a cheater, period.