Regression toward the mean

[Orton's Arm]

Uhhh...because they can read?

Why on earth not?  I don't need to "win".  I'm right, and you're an idiot.  There's nothing for me to "win"...no matter what happens, I'm still right and you're still an idiot.

873560[/snapback]

I guess those quotes from Stanford, Berkeley, the University of Chicago, and the other sources I mentioned must have been written by idiots too then. Because they say the same thing I've been saying all along.

[Bungee Jumper]

I guess those quotes from Stanford, Berkeley, the University of Chicago, and the other sources I mentioned must have been written by idiots too then. Because they say the same thing I've been saying all along.

873575[/snapback]

 

No, they don't. You just don't understand them.

[Ramius]

But it's so much !@#$ing fun to read, i'n't it?   

873563[/snapback]

 

Agreed. His gross incompetence on this topic has gotten to the point where i have almost pissed myself while laughing at some of the utter crap he's written.

 

I'm going to try the holcombs arm method for my next presentation. I am going to not read or understand a paper, like he does, and then when i am questioned, i am going to say "its from berkeley!"

[Ramius]

I guess those quotes from Stanford, Berkeley, the University of Chicago, and the other sources I mentioned must have been written by idiots too then. Because they say the same thing I've been saying all along.

873575[/snapback]

 

No, they actually say something different, you are just too stoopid to realize what they hell they are really saying.

 

you dont even understand what the hell you are trying to aruge

 

and i guess thats what makes this so funny.

[Bungee Jumper]

Agreed. His gross incompetence on this topic has gotten to the point where i have almost pissed myself while laughing at some of the utter crap he's written.

 

I'm going to try the holcombs arm method for my next presentation. I am going to not read or understand a paper, like he does, and then when i am questioned, i am going to say "its from berkeley!"

873578[/snapback]

 

Hey, it works on the sports side of the board: "This story says Losman sucks and Holcomb should be starting! It's from ESPN!" Why not here?

[Bungee Jumper]

No, they actually say something different, you are just too stoopid to realize what they hell they are really saying.

 

you dont even understand what the hell you are trying to aruge

 

and i guess thats what makes this so funny. 

873581[/snapback]

 

It's like watching a three-year old play-act at being an adult. Just so cute, because they think they're acting adult, but they have no idea...

[Wraith]

Thanks, i know what positive correlation is. Berkeley was implying that the positive correlation had some bearing on the directionality of the scores when the test was re-taken.

 

That was what i was questioning, because as you stated, that implication is bull sh--. Holcombs arm is just too stupid to realize this.

873539[/snapback]

 

Right, I assumed you know what positive correlation is. What I'm saying is that I don't think this author meant to imply that the positive correlation is causing movement towads the mean. I'm trying to say that the author is simply pointing out that, even with the movement towards the mean, the scores tend to stay on the same of the mean due to the positive correlation between test and retest.

 

Lifting a few sentences or even a few paragraphs from the text is what is causing the apparent implication.

[Orton's Arm]

What we find is that those that scored exceptionally high (or low) on the first measurement score closer to the mean on the second measure; that is, there is regression to the mean. The greater the error component, the greater will be the regression or "turning back" to the mean.

Suppose you were told that when any group of subjects with low values on some measurement is later remeasured, their mean value will increase without the use of any treatment or intervention. Would this worry you? It sure had better! . . .

 

The behavior described in the first paragraph is real. It is called the regression effect.

In most test-retest situations . . . those who perform best usually do so with a combination of skill (which will be present in the retest) and exceptional luck (which will likely not be so good in a retest). Those who perform worst usually do so as the result of a combination of lack of skill (which still won't be present in a retest) and bad luck (which is likely to be better in a retest). . . . A particularly high score could have come from someone with an even higher true ability, but who had bad luck, or someone with a lower true ability who had good luck. Because more individuals are near average, the second case is more likely; when the second case occurs on a retest, the individual's luck is just as likely to be bad as good, so the individual's second score will tend to be lower. The same argument applies, mutatis mutandis, to the case of a particularly low score on the first test.

 

Regression Effects

 

The tendency of subjects, who are initially selected due to extreme scores, to have subsequent scores move inward toward the mean. Also known as statistical regression/regression to the mean/regression fallacy.

 

Regression effect: in almost all test-retest situations

- The bottom group on the first test will on average show some improvement on the second test

- The top group on the first test will do a bit worse on the second test

-  Regression fallacy: thinking that the regression effect must be due to something important, not just spread around the SD line.

 

If two successive trait measurements have a less-than-perfect correlation, individuals or populations will, on average, tend to be closer to the mean on the second measurement (the so-called regression effect).

 

Take people who scored 140 on the test. Two possibilities:

• a) true score below 140, positive chance error (T < 140, + error) e.g. 135+5

• b) true score above 140, negative chance error ( T > 140, - error) e.g. 145-5

A plot of the normal curve shows that the first explanation is more likely – the true score is most likely lower, and so on average, the scores on the second test will be a bit lower than the first.

I don't see why Ramius and Bungee Jumper expect anyone to be stupid enough to believe I don't understand the quotes I've found. Anyone who's a) been paying at least some attention to this debate, and b) has at least a few working brain cells, will see that those quote communicate exactly the same message I've been trying to get through for the last 50 pages. I just don't see how anyone on these boards could possibly be stupid enough to buy what Ramius and Bungee Jumper are selling.

[Bungee Jumper]

I don't see why Ramius and Bungee Jumper expect anyone to be stupid enough to believe I don't understand the quotes I've found. Anyone who's a) been paying at least some attention to this debate, and b) has at least a few working brain cells, will see that those quote communicate exactly the same message I've been trying to get through for the last 50 pages. I just don't see how anyone on these boards could possibly be stupid enough to buy what Ramius and Bungee Jumper are selling.

873596[/snapback]

 

The problem isn't the quotes. The problem is the retard doing the quoting. You still can't distinguish between error and variance. No matter how many things you link to "proving" your "point", you'll misunderstand them and be wrong until you somehow, miraculously, unexpectedly learn to distinguish between error and variance.

[Orton's Arm]

The problem isn't the quotes.  The problem is the retard doing the quoting.  You still can't distinguish between error and variance.  No matter how many things you link to "proving" your "point", you'll misunderstand them and be wrong until you somehow, miraculously, unexpectedly learn to distinguish between error and variance.

873655[/snapback]

The quotes I've provided are correct. The quotes I've provided indicate that generally, those who obtain very high or very low scores on tests tend to regress toward the population mean upon being retested. Your attempts to make fun of this phenomenon have made you look both stupid and ignorant--especially now that I've found numerous sources describing the phenomenon I've been describing. Now, you seem to be trying to distract attention from all the confusion and error you've been sowing by pretending I don't know the difference between error and variance. That's pitiful.

 

In fact, everything about your participation in this discussion has been pitiful. I provided the I.Q. test example, which you ridiculed. Well guess what? Your decision to engage in ridicule sure looks pitiful in light of the fact that the Stanford website provided essentially the same example I provided. They said basically the exact same thing. Oh, oh, let me guess: because it's Stanford, their example of lucky 135s/unlucky 145s takes the difference between error and variance into account, whereas my example of lucky 130s and unlucky 150s shows a complete incomprehension of the issue. Am I really supposed to respect you after seeing you engage in such idiocy or such lack of intellectual honesty? You're being pitiful either way.

[Bungee Jumper]

The quotes I've provided are correct.

873661[/snapback]

 

The quotes are correct (except the Berkely one). YOU are wrong. You don't even understand the crap you're using to prove your point.

[KurtGodel77]

The quotes I've provided are correct. The quotes I've provided indicate that generally, those who obtain very high or very low scores on tests tend to regress toward the population mean upon being retested. Your attempts to make fun of this phenomenon have made you look both stupid and ignorant--especially now that I've found numerous sources describing the phenomenon I've been describing. Now, you seem to be trying to distract attention from all the confusion and error you've been sowing by pretending I don't know the difference between error and variance. That's pitiful.

 

In fact, everything about your participation in this discussion has been pitiful. I provided the I.Q. test example, which you ridiculed. Well guess what? Your decision to engage in ridicule sure looks pitiful in light of the fact that the Stanford website provided essentially the same example I provided. They said basically the exact same thing. Oh, oh, let me guess: because it's Stanford, their example of lucky 135s/unlucky 145s takes the difference between error and variance into account, whereas my example of lucky 130s and unlucky 150s shows a complete incomprehension of the issue. Am I really supposed to respect you after seeing you engage in such idiocy or such lack of intellectual honesty? You're being pitiful either way.

873661[/snapback]

I'm assuming you know that in the U.S., anti-slavery laws make it illegal for one human being to own another. That makes you an outlaw, because never has one human being owned another more thoroughly than you've owned Bungee Jumper. Congratulations.

[Bungee Jumper]

I'm assuming you know that in the U.S., anti-slavery laws make it illegal for one human being to own another. That makes you an outlaw, because never has one human being owned another more thoroughly than you've owned Bungee Jumper. Congratulations.

874077[/snapback]

 

That would carry more weight if you weren't equally ignorant.

[Sketch Soland]

It seems like Wraith is the only one who's really noticed that this whole argument pages and pages ago morphed from a quasi-debate on statistics to a semantic pissing contest as to who could repeat their own perspective in the most assinine manner for the longest period of time.

 

It is obvious that both sides have equally valid points on this issue, from differing perspectives that address the problem with different semantic matrices. Hence the "error" vs. "Variance" argument, "luck" vs. "variance" argument, and the "mean" vs. "population mean" argument, and the various interpretations of what it means to "regress".

 

If both sides could agree on the meanings of the words used to discuss the issue, I think you would both find that neither side is completely "right" or "wrong" but merely offering slightly differing perspectives that basically recognize the heart of the question while explaining it with slightly differing vocabulary.

 

You don't have to be a statistics expert to recognize this. I don't claim to have the be all and end all answer, but you guys are more frikkin' hysterical than two six year old girls arguing over who gets to play with a barbie doll.

[Bungee Jumper]

It seems like Wraith is the only one who's really noticed that this whole argument pages and pages ago morphed from a quasi-debate on statistics to a semantic pissing contest as to who could repeat their own perspective in the most assinine manner for the longest period of time.

 

It is obvious that both sides have equally valid points on this issue, from differing perspectives that address the problem with different semantic matrices.  Hence the "error" vs. "Variance" argument, "luck" vs. "variance" argument, and the "mean" vs. "population mean" argument, and the various interpretations of what it means to "regress".

 

If both sides could agree on the meanings of the words used to discuss the issue, I think you would both find that neither side is completely "right" or "wrong" but merely offering slightly differing perspectives that basically recognize the heart of the question while explaining it with slightly differing vocabulary.

 

You don't have to be a statistics expert to recognize this.  I don't claim to have the be all and end all answer, but you guys are more frikkin' hysterical than two six year old girls arguing over who gets to play with a barbie doll.

874240[/snapback]

 

No, I knew that. It's just fun to watch HA thrash around like a landed fish.

[Alaska Darin]

No, I knew that.  It's just fun to watch HA thrash around like a landed fish.

874289[/snapback]

Wrong. Even Salmon know when to give up.

[Orton's Arm]

It seems like Wraith is the only one who's really noticed that this whole argument pages and pages ago morphed from a quasi-debate on statistics to a semantic pissing contest as to who could repeat their own perspective in the most assinine manner for the longest period of time.

 

It is obvious that both sides have equally valid points on this issue, from differing perspectives that address the problem with different semantic matrices.  Hence the "error" vs. "Variance" argument, "luck" vs. "variance" argument, and the "mean" vs. "population mean" argument, and the various interpretations of what it means to "regress".

 

If both sides could agree on the meanings of the words used to discuss the issue, I think you would both find that neither side is completely "right" or "wrong" but merely offering slightly differing perspectives that basically recognize the heart of the question while explaining it with slightly differing vocabulary.

 

You don't have to be a statistics expert to recognize this.  I don't claim to have the be all and end all answer, but you guys are more frikkin' hysterical than two six year old girls arguing over who gets to play with a barbie doll.

874240[/snapback]

There's some truth to this post. But Bungee Jumper and I have arguing about more than just semantics here. I've written that if an I.Q. test involves measurement error, someone who obtains a very high or low score on the first test taking will, on average, score closer to the population's mean upon being retested. Because I voiced this sentiment, Bungee Jumper has questioned my intelligence, my knowledge of statistics, and has indulged in endless "regression toward the mean" jokes at my expense. He's wandered into threads that had nothing to do with me or with the issues we've been debating, and announced his opinion that I belong in a list of the stupidest posters on this board.

 

Fortunately, I've found quotes from sources like Stanford, Berkeley, the University of Chicago, and others, which prove that my description of the phenomenon was correct, and Bungee Jumper's ridicule was absurd. Given the abuse he's shoveled my way, I'm not willing to pretend that Bungee Jumper was aware of this phenomenon all along. He wasn't; and he discouraged others from believing in it.

 

If the debate now seems to be about semantics, it's because Bungee Jumper is no longer (directly) disputing the phenomenon I've worked so hard to describe. But he still feels the need to call me an idiot, and to prove to the world that I must have been wrong about something or another. So now he's turned to vague and unsupported accusations--"you're too stupid to understand the difference between variance and error" would probably be a run of the mill Bungee Jumper post. He eschews the idea of providing information about a) how he thinks I'm defining variance and error, b) how he thinks those terms should be defined, and c) how the difference between a) and b) has supposedly caused a mistaken understanding of the underlying issue. In other words, he's deliberately vague, and avoids getting pinned down. As long as he continues to ridicule something from what I've been saying, he appears to the casual observer to have been consistent.

 

On one level, this is a debate about whether the statistical phenomenon I've been describing exists. But more than that, it's about Bungee Jumper's need to ridicule me about something. So he'll make vague accusations--"you don't understand the articles you're quoting"--not because he thinks these things are true, but because he hopes that others reading this thread will believe the accusations. Most people aren't very confident in their knowledge of stats. Bungee Jumper knows this, and hopes these people will conclude that there's some hidden or mysterious meaning in the quotes I've found, which he was (supposedly) smart enough to see; but which I could not see. He provides no insight into what that alleged hidden meaning might actually be. In general, he's aware that vague accusations--"you're too stupid to understand the article" are harder to refute than specific accusations.

 

Bungee Jumper's communication style doesn't lend itself to the edification of the audience. Very rarely will he attemt to provide actual information about statistics. Consider his statement that I can't distinguish between error and variance. A claim like that cannot possibly be expected to enlighten either myself or any third party reading this thread. He makes no effort to explain this difference; nor to show its relevance to our debate. Those reading this thread are expected to blindly take his word that I don't understand these things, and that this misunderstanding somehow demolishes the points I've been making. Most people don't have the self-confidence in their knowledge of stats to see the absurdity of his claims. They incorrectly assume that if a physicist like him is throwing this type of accusation my way, there must be at least some truth to it. There isn't, but how can people know?

 

I regret that I've sunk to his level as far as name-calling goes. But I've tried to avoid sinking to his level in other ways. Instead of trying to win debates by making vague, Bungee Jumper-style accusations, I try to make the audience a little richer in knowledge than it otherwise would have been. I do not deliberately deceive or mislead people. I tell the truth as I see it. I don't throw insults at people unless they first insult me. These things aren't much, and I'm certainly not claiming to be a saint. But they're at least something.

[Bungee Jumper]

There's some truth to this post. But Bungee Jumper and I have arguing about more than just semantics here. I've written that if an I.Q. test involves measurement error, someone who obtains a very high or low score on the first test taking will, on average, score closer to the population's mean upon being retested. Because I voiced this sentiment, Bungee Jumper has questioned my intelligence, my knowledge of statistics, and has indulged in endless "regression toward the mean" jokes at my expense. He's wandered into threads that had nothing to do with me or with the issues we've been debating, and announced his opinion that I belong in a list of the stupidest posters on this board.

 

Fortunately, I've found quotes from sources like Stanford, Berkeley, the University of Chicago, and others, which prove that my description of the phenomenon was correct, and Bungee Jumper's ridicule was absurd. Given the abuse he's shoveled my way, I'm not willing to pretend that Bungee Jumper was aware of this phenomenon all along. He wasn't; and he discouraged others from believing in it.

 

If the debate now seems to be about semantics, it's because Bungee Jumper is no longer (directly) disputing the phenomenon I've worked so hard to describe. But he still feels the need to call me an idiot, and to prove to the world that I must have been wrong about something or another. So now he's turned to vague and unsupported accusations--"you're too stupid to understand the difference between variance and error" would probably be a run of the mill Bungee Jumper post. He eschews the idea of providing information about a) how he thinks I'm defining variance and error, b) how he thinks those terms should be defined, and c) how the difference between a) and b) has supposedly caused a mistaken understanding of the underlying issue. In other words, he's deliberately vague, and avoids getting pinned down. As long as he continues to ridicule something from what I've been saying, he appears to the casual observer to have been consistent.

 

On one level, this is a debate about whether the statistical phenomenon I've been describing exists. But more than that, it's about Bungee Jumper's need to ridicule me about something. So he'll make vague accusations--"you don't understand the articles you're quoting"--not because he thinks these things are true, but because he hopes that others reading this thread will believe the accusations. Most people aren't very confident in their knowledge of stats. Bungee Jumper knows this, and hopes these people will conclude that there's some hidden or mysterious meaning in the quotes I've found, which he was (supposedly) smart enough to see; but which I could not see. He provides no insight into what that alleged hidden meaning might actually be. In general, he's aware that vague accusations--"you're too stupid to understand the article" are harder to refute than specific accusations.

 

Bungee Jumper's communication style doesn't lend itself to the edification of the audience. Very rarely will he attemt to provide actual information about statistics. Consider his statement that I can't distinguish between error and variance. A claim like that cannot possibly be expected to enlighten either myself or any third party reading this thread. He makes no effort to explain this difference; nor to show its relevance to our debate. Those reading this thread are expected to blindly take his word that I don't understand these things, and that this misunderstanding somehow demolishes the points I've been making. Most people don't have the self-confidence in their knowledge of stats to see the absurdity of his claims. They incorrectly assume that if a physicist like him is throwing this type of accusation my way, there must be at least some truth to it. There isn't, but how can people know?

 

I regret that I've sunk to his level as far as name-calling goes. But I've tried to avoid sinking to his level in other ways. Instead of trying to win debates by making vague, Bungee Jumper-style accusations, I try to make the audience a little richer in knowledge than it otherwise would have been. I do not deliberately deceive or mislead people. I tell the truth as I see it. I don't throw insults at people unless they first insult me. These things aren't much, and I'm certainly not claiming to be a saint. But they're at least something.

874604[/snapback]

 

It is utterly amazing that you are so unshakeably confident in your complete ignorance. Have you ever even calculated an integral? You have not made ONE post that shows you have any knowldege of any of the subjects you're trying to discuss. Not one. Hell, you still can't define variance...after about a thousand posts. Given that it speaks directly to nearly every single matter you've brought up...your complete ignorance of it is telling.

 

You have, however, provided us with such brilliance as "a die regresses to the mean of 3.5" and "a rubber band stretches because of error". I'm pretty sure the reading public is clear you haven't got a clue.

 

Not that anyone's reading this anymore. Most people have just accepted you're a complete dolt and moved on. I would have...but like I said, your delusions, such as the above, entertain me.

[Orton's Arm]

It is utterly amazing that you are so unshakeably confident in your complete ignorance.  Have you ever even calculated an integral?  You have not made ONE post that shows you have any knowldege of any of the subjects you're trying to discuss.  Not one.  Hell, you still can't define variance...after about a thousand posts.  Given that it speaks directly to nearly every single matter you've brought up...your complete ignorance of it is telling.

 

You have, however, provided us with such brilliance as "a die regresses to the mean of 3.5" and "a rubber band stretches because of error".  I'm pretty sure the reading public is clear you haven't got a clue. 

 

Not that anyone's reading this anymore.  Most people have just accepted you're a complete dolt and moved on.  I would have...but like I said, your delusions, such as the above, entertain me. 

874692[/snapback]

All real debate ended when I provided the quotes from Stanford, Berkeley, the University of Chicago, et al. Nothing you can possibly say will detract from the truth of those quotes. The quotes say that in test/retest situations, those who obtain extreme scores on the first test will tend to score closer to the population mean upon being retested. I've been so abundantly clear on that issue that nothing you now say will confuse people into believing that I've said otherwise. Unfortunately for yourself, you've been so prolific in mocking my view of this that you can't weasel out now.

 

You've made a complete fool out of yourself. Deal with it.

[Bungee Jumper]

All real debate ended when I provided the quotes from Stanford, Berkeley, the University of Chicago, et al. Nothing you can possibly say will detract from the truth of those quotes. The quotes say that in test/retest situations, those who obtain extreme scores on the first test will tend to score closer to the population mean upon being retested. I've been so abundantly clear on that issue that nothing you now say will confuse people into believing that I've said otherwise. Unfortunately for yourself, you've been so prolific in mocking my view of this that you can't weasel out now.

 

You've made a complete fool out of yourself. Deal with it.

874712[/snapback]

 

I'm not disputing the quotes from Stanford or anyone (save Berkely, which was really weird). They all say exactly what I've been saying: excessive error will regress to the mean OF THE ERROR.

 

I'm disputing your interpretation of them, that it represents regression to the population mean. It doesn't. You don't understand the difference between error and population variance. Hell, you don't even understand the difference between an individual and a population, apparently. And you still don't understand what that effect means: it means, simply, that you've arbitrarily picked a sample with high net error. Period. That's why I called it a completely fictitious effect earlier - becaues it only exists if you specifically look for it. In the limit of an entire population, it doesn't mean a damned thing.

 

But unless you are saying now that this is NOT regression toward the population mean, you're still wrong. And if you're saying that now...you're trying to weasel out of your earlier idiot statements.