Statistics 101

No I get it, really I do. I just feel there is more to it.Expertise is relavant.

hi riverrat,the one that will really freak you out is the monty hall problem.You have three closed doors in front of you. Behind one of them is a car, and behind each of the other two there is a goat. You pick a door. One of the OTHER doors is opened, revealing a goat. If you want to win the car, should you stick with the door you initially chose, or should you switch to the other door which has not yet been opened?in edit - obviously if you google you can find the explanation, so fair play everyone! [This is a fascinating problem that has come up before here at EvC Forum. I'd like to extend Mick's request for fair play to everyone who already knows the answer. If you already know the answer to this, please hold back so that people who are seeing it for the first time can mull it over and discuss it for a while. --Admin]MickEdited by mick, : No reason given.Edited by mick, : No reason given.Edited by mick, : No reason given.Edited by Admin, : Add administrative request.

Yea, it did freak me out, I admit, I cheated, I looked it up in wikipedia, and I would have answered that it was a 50/50 chance.But this sort of explains how time is a factor in determining odds.

*headslap*

was that called for?
really....

When you say stupid stuff? Yeah.

If time doesn't count, then the person in the monty hall problem should only have a 50/50 chance of guessing the right door, right?
It shouldn't matter if there was a 66% chance of picking a donkey.I see how it relates to what I have been saying. There are things that are unforseen crashfrog. Your expertise, or anyone elses for that matter are only relavent to current knowledge. That is why I say if you play the lotto, there is a million (or 146 million) combunations, but if you win on your first try, then your odds where 1-1.Ask a determinists if it is possible or not.

Time doesn't have anything to do with it.Think of it this way. You pick a door. Not knowing anything else, you know that there's a 2/3 chance that the car is behind one of the other two doors.When Monty opens one of the doors, it's not like the car moves or something, so the chance that you were wrong doesn't change - but now there's only one other door to pick. You still only have a 1/3 chance of your first guess being right. Leaving only one door, that means that if you change your guess to the other door, your odds of winning the car are now 2/3.That's how it makes sense for me, anyway. It's not about changing probabilities over time. (If they changed, 50/50 would be the right answer.) It's precisely because the odds don't change that changing your guess is so advantageous.

It has been discussed earlier in this thread. It's information, not time that is the difference. I've been continually correcting Crash on that score in this thread and it's a shame that you picked up on his misrepresentation of the facts.Before Monty opens a door, you know that there is a 2/3 chance that one of the other two doors is a winner. Because Monty deliberately chooses an unopened door (you need to knwo that he does that, and that he always does it) he removes that from consideration. So there is now a 2/3 chance that the remaining door is the winner.So Crash is right to say that it is not time that matters and dead wrong to say that the probability hasn't changed. The information you have means that the probability of the remaining door being the winner is now 2/3 as Crash knows - but it's because you have that information, not because time is a factor in itself.Note that the solution IS dependant on how Monty chooses doors. If he chose a door at random and it happened not to be the winning door the probability of the remaining door being the winner DOES go to 0.5 - along with the door you chose. See Message 46 for a brief description of the math.And if Monty doesn't always open a door there is another factor to consider. Suppoe that Monty only opens a door when the contestant chose the winning door ? Switching then would have no chance of winning but sticking would be a guaranteed win ! It's information that makes the difference and you have to know how Monty chooses which door to open.(And Crash please stop confusing RR. You know damn well that the probability of the remaining door winning is 2/3 and that of the opened door is 0/3. Please don't insist that you should still use the 1/3 probability for each - as you do every time you say "the probabilities don't change". Because if you do you disagree with the solution that you know is right - if you use the 1/3 probabilities you are just as likely to win by switching to the open door - known to be a loser - as you are by choosing the remaining door ! You KNOW that the answer relies on moving that 1/3 from the opened door to the remaining unopened door ! So why try to insist that that doesn't and can't happen ?)

I'm not saying your wrong, but when you say "Time doesn't have anything to do with it."Then proceed to describe the whole thing with words like: When, first, and change. Those phrases all involve time.Your chances are increased because of another pick, which happens over time. Just like if you play the lotto 146 milliontimes.In a conceptual world, time would not be a factor.

Without time, this problem doesn't get a chance to happen, in the real world. Even on paper, or in concept, both events can't happen at the same time.

Your objection shows that you do not understand my point.As I said, it is not the passage of time in itself that matters but the availability of new information, that allows you to reassess the probabilities in the light of that information. If Monty didn't open that other door you could wait for eternity and you wouldn't be any better off.It is the fact that you have additional information that matters - not how long it took you to get it.

Which I've never denied. Your reply here is simply a misrepresentation of what I've been posting - something you've been doing throughout.But, you know, whatever. Anybody can see that RR has picked up on your faulty understanding of probability; that's why he's insisting that time is a factor.Before he opens a door, you know that the odds that you've chosen the right door are only 1/3. After he opens a door, the only thing that is different is that you know which of the other two doors not to choose. Since your odds of being right the first time haven't changed, the odds that it's the other door must (by process of elimination, if you will) be 2/3.If the odds did change with time, it would be 50/50. Everybody knows that it isn't. Misrepresenting me isn't going to make things any clearer for Riverrat, and the repeated insistence by some that probabilities are different in the future than in the past - a concept with no mathematical basis that I can discern - is the source of his current confusion. So point that finger back at yourself, Paulk.

Dude, why are you so resistant to this?The Monty Hall problem is quite difficult and most people (including me) get it wrong.This one is far easier.

quote:

---

Which I've never denied. Your reply here is simply a misrepresentation of what I've been posting - something you've been doing throughout.

---

So you never insisted that the probabilities don't change ? And you've got no business complaining about misrepresentation on this thread.

quote:

---

But, you know, whatever. Anybody can see that RR has picked up on your faulty understanding of probability; that's why he's insisting that time is a factor.

---

Anyone can see that he's picked up on YOUR misrepresentation. You're the one that put forward that idea.

quote:

---

If the odds did change with time, it would be 50/50.

---

That's silly. Firstly because there's no relation between time and the odds. Secondly the odds do change because of the information. And thirdly as I have pointed out, if Monty opens a door at random and it happens not to be the winner the odds DO change to 50/50.

quote:

---

Misrepresenting me isn't going to make things any clearer for Riverrat, and the repeated insistence by some that probabilities are different in the future than in the past - a concept with no mathematical basis that I can discern - is the source of his current confusion. So point that finger back at yourself, Paulk.

---

I'm not misrepresennting you. You are misrepresenting me AND it is your misrepresentaions that are confusing RR. This whole "probabilities change with time" is YOUR invention. Nobody else said it.