Ten fold

12:42 AM

@Stephan On "mods commenting on unclear questions and requesting clarification. It seems like less than 10% of such questions are ever clarified" ... in spite of whuber stepping up to take a bullet there that problem is much more my fault than his, because I often don't follow them up. If I can't come back later (and really there's a bunch more stuff to deal with every time) I should lean toward closing on the spot.

Re failure to follow up or time-delayed closure ... I did ask for something related to that here -- something to make it easier to follow these up and close them (among other tasks). It was closed as a dupe of something I explicitly excluded from my question, but from the look of it would have suffered exactly the same fate (i.e. status-declined) if it had not.

I agree with whuber -- if you see a question (including one with comments asking for clarification or indeed any other interaction from a moderator) that you think should close just vote to close. You have moderator-level-privileges ("access to moderator tools" privilege) for a reason.

@matt I remember the 1996 game. Played it a few times

[But then I remember talking (via email) with Peter Adkinson a number of times while Wizards were trying to get Magic:the Gathering to market but were in danger of going under from a lawsuit before they got it there.]

Glen_b

1:42 AM

reading here:

fivethirtyeight.com/features/…

> natesilver: Well, Micah, it depends on what you mean by “substantially.” And by “battleground.”

> micah: You’re a pedant.

No, that just sounds like a statistician to me. Though perhaps that's because often a statistician is either pedantic or wrong.

2

Dawny33

5:22 AM

@Glen_b So, is it okay to as it on the main site (http://chat.stackexchange.com/transcript/message/30379856#30379856)

Or, is it just a stupid/random unverified quote?

Stephan Kolassa

6:00 AM

@Glen_b ... and sometimes statisticians are both pedantic and wrong!

Dawny33

In fact, I find statisticians being pedantic more often than not

Glen_b

6:32 AM

@Stephan indeed. Sometimes necessary but never sufficient.

@Dawny I am not sure what you're asking. Is it okay to do what?

@amoeba 42% after 76 presses.

No equipment needed either, I did that using my head (there was a trick to it, though)

Dawny33

6:55 AM

@Glen_b Ask on the main site. (Mis-typed "ask" as "as")

Stephan Kolassa

7:09 AM

@Dawny33 I'd just post my comment as an answer: chat.stackexchange.com/transcript/message/30381000#30381000

If you think this question & answer combination will be helpful for future generations, do ahead and post.

If you hope for a better answer, post your question too - and if possible, note what, if anything, you don't think is helpful about my comment.

Dawny33

@StephanKolassa Actually, your comment makes complete sense, especially the:

"Any patterns can be detected and exploited in repeated play."

Was just lingering around to see if anyone challenges your comment :)

Just a doubt: The learning of those patterns is `reinforcement learning`, right?

Stephan Kolassa

Reinforcement learning

Reinforcement learning is an area of machine learning inspired by behaviorist psychology, concerned with how software agents ought to take actions in an environment so as to maximize some notion of cumulative reward. The problem, due to its generality, is studied in many other disciplines, such as game theory, control theory, operations research, information theory, simulation-based optimization, multi-agent systems, swarm intelligence, statistics, and genetic algorithms. In the operations research and control literature, the field where reinforcement learning methods are studied is called ...

If you want to put a fancy label in it, you can call it so. It seems to fit the definition as per Wikipedia.

However, if my seven-year-olds play rock-paper-scissors in the school yard, notice their equally seven-year-old opponent exhibits some kind of pattern, and then proceed to exploit this pattern, I'd call that plain vanilla learning and not put a fancy name on it.

Dawny33

7:30 AM

Pretty neat example. Thank you :)

amoeba

9:35 AM

@Glen_b Wow, did you achieve 42% after reading about what algorithm the program uses or without reading it? If you did it without, I am very curious as to how. Actually, do you think I can ask this as a question on the main site? This could be fun.

Glen_b

10:47 AM

@amoeba I didn't read about how it worked, I simply assumed it would be very good at spotting patterns humans tend to come up with. So I used a sequence of numbers I didn't come up with that appears to be random but which I know (or rather, I know how it starts) and converted that into F's and D's (by the simple expedient of looking at whether it was even or not).

Which is to say I just used digits of pi. It's a tool I have often used before -- e.g. when playing rock, paper scissors against better players than myself. It can be very handy at times.

Of course 42% is essentially just random variation about 0.5 -- it could as easily have resulted in 58%

Stephan Kolassa

@Glen_b You know pi to 76 digits? I'm impressed.

Glen_b

I used to be able to rattle it off to many more, but there's not much call for it.

Stephan Kolassa

42% out of 76 trials is not yet statistically significant, binom.test(32,76), p=0.21...

Glen_b

I had to struggle for the last few; I may have skipped some digits in there.

@StephanKolassa hence my comment above about it just being random variation about 0.5

I didn't need to test it to see it wasn't significant. Two standard errors is 1/sqrt(76)

which is obviously more than 0.1

So |0.42-0.5| = 0.08 is nowhere near a p-value of even 5%

Of course to accept there was really something going on (like a claim of being able to "beat" the algorithm) I'd be using a substantially lower significance level than 5%

It was just a trick I thought might work well enough.

Usually I don't manage to recall quite so many digits. Most days I can get 50-odd before I struggle.

Sometimes it's easier than other times.

:

Glen waves to Scortchi

The memory isn't what it was.

The other day I was talking to someone I had met a couple of times many years ago and he said "I always remember you because the second time we met you remembered my phone number from the first time we met. You said but it's easy, because it's divisible by 13."

It was actually much easier than that because every pair of digits was divisible by 13

But that was back when I could memorize phone numbers at will.

Can't do that any more

He was more impressed that I could tell it was divisible by 13 than by the fact I could recall it a month later... which was actually the least tricky part, since you could see that at a glance

Often people who aren't used to some basic mental arithmetic can be inordinately impressed by simple tricks though

I've had students gape open mouthed when I do problems in my head quicker than they can type them into a calculator... even when there's only simple arithmetic

I guess mental calculation's not something people do much any more.

But if I don't already know what the answer is, more or less, why would I trust I typed it in correctly?

Ah well, things to do

...

Bye all

whuber

2:03 PM

@Glen_b I used digits of pi, too, but did not achieve the same results. The problem was that I tried base 10 and base 6, but binary of course would have been the obvious choice.

Glen_b

3:49 PM

@whuber I did base 10, taking odd and even (I contemplated working in binary but it seemed like more effort than I cared to invest). The only questions were whether to start with 3 or with 1 and whether F was evens or D was evens.

General Abrial

5:50 PM

@Glen_b I'm imagining the techs

that maintain that page are reviewing the logs and discover "wow, yesterday everyone suddenly got really good at this!"

Matthew Drury

7:51 PM

The grocery store by my apartment has the express lanes organized in a square, with two stations on each side, for a total of four stations.

These are manned stations, you can't checkout yourself (groan).

Often there are only one or two attendants on duty.

And when there are two, they are always stationed on opposite sides of the square, forcing the customers to make two lines.

If they were on the same side of the square, the customers would form one line, and the head of line customer would always get the first free attendant.

This inefficiency drives me nuts, but I'm too introverted to point it out.

Stephan Kolassa

@MatthewDrury I was waiting for the connection to statistics. Now I know: inefficiency.

whuber

8:08 PM

@StephanKolassa Queuing theory.

Glen_b

11:14 PM

I was interested to watch the Mythbusters test out queueing theory -- they made a mock up grocery store/supermarket with volunteer customers and gave the customers varying lists of things to find and queue for and pay for (with fake money) and 10% (I think) of customers had something that would make checkout take longer. After running the system for a while they recorded how long people took to get from joining the queue to exiting the system

They did this for multiple servers with multiple lines and single lines. Their results were of course not sufficiently replicated but did suggest that the single line took longer on average. It made me wonder which assumption or assumptions failed that most contributed to what they saw.

However, they did find that the people in the single line were happier about their time waiting even though they waited longer on average (and it was fairer in that the very longest waits were eliminated).

It's a pity there wasn't time to investigate in more depth what was going on.

One issue they did suggest was that the time taken to get from the head of the single line to a server was a factor, but it was a matter of seconds (something like six on average) while the difference in mean waiting time was much larger

Transcript for