Orton's Arm

Assuming that stats book mentions regression toward the mean at all (which it may not), it will support what I've been saying. You haven't found any links to anything which would support the ignorant fallacies you've been spouting. You say that it's not your position, it's math. Well, how about doing the math you said you would do? Here's what you promised: Let's see some action--math, links to sources that actually support you, something. Because you've done absolutely nothing this whole discussion except create a whole lot of hot air.

Suppose someone scores 140 on an I.Q. test. This person is planning on taking the test a second time. At first glance, you'd think the person's expected score the second time around would be another 140. That isn't the case--the expected score on the retest will be somewhere in the 120s or 130s. There are three possibilities here: a 140 score could indicate someone with an I.Q. of 140. It could indicate someone with a lower I.Q. (130 for example) who got lucky on the test. Or it could indicate someone with an I.Q. of 150 who got unlucky. Of these three possibilities, the second is far more likely than the third. Therefore, the average person who gets a 140 on an I.Q. test has an I.Q. that's less than 140. On average someone who gets a 140 on an I.Q. test will get a somewhat lower score upon being retested. It took Wraith a while to realize that supposed statistics experts such as Bungee Jumper and Ramius were disputing this widely-known, non-controversial phenomenon. But once he realized what the argument was about, he took my side.

It's very frustrating to argue with someone who A) is as totally wrong as you, B) refuses to provide links to support his position, and C) tries to make up for all this by repeatedly providing a link to a purchase opportunity for a stats book. There's a very simple reason you can't find a single article from a credible source with which to support your position on regression toward the mean. There's a reason I'm able to find a number of articles from unrelated sources which support my position.

I'm using the metaphor correctly. Measurement error causes the rubber band to stretch. Remeasuring those with the most extreme scores causes it to snap back into place. Let me put it to you this way: suppose you had a group of people that all had an I.Q. of 100. You give them an I.Q. test. Some get lucky and get a 110, others get unlucky and get a 90, and still others get a 100 on the test. Measurement error is causing this group's I.Q.s to appear to be more spread out than they really are--like the stretching of a rubber band. Next, you gather up those who scored a 90 on the I.Q. test, and ask them to take the test a second time. Some will once again get an unlucky 90; others will get lucky 110s; and still others will get correctly scored at 100. On average, this group's score on the second test will be 100. The rubber band snaps back into place.

Thanks for making up random stuff, and putting words in my mouth. You're really adding to things here. No, really. Keep up the good work.

And several other sources. As compared to the zero links you've provided which support your view. If your view of regression toward the mean was correct (it isn't) don't you think you'd be able to find links somewhere to support it? If statistics textbooks supported your view (which they don't) don't you think you'd be able to find a direct quote from one of them which would say so?

Wow! You've found a link to a place that lets you buy a statistics textbook! That must mean that every word you've ever written about stats is 100% correct! I've found links to actual articles which confirm what I've been saying all along about regression toward the mean. Since you weren't able to understand those articles, you might want to buy that stats book for yourself.

Let's let Wraith be the judge of whether I've understood his posts or not.

No. I've done enough. I've provided links to credible sources which support what I've written about regression toward the mean. You've provided no links whatsoever to any sources which support your view. If you're unwilling to research this topic for yourself, or unable to understand what it is you've researched, that's your problem.

It's posts like the above which utterly remove the possibility of you having credibility. If you're going to throw around insults about free clinics, at least make sure your facts are straight first. Wraith wrote that regression toward the mean is caused by a two part process. First, measurement error on the first test causes a distribution to appear to be more spread out than it really is. He compared this to the stretching of a rubber band. The second part of this process is when you re-measure those with the most extreme scores. On average, those scores will drift a little closer to the mean the second time around. This second part of the process is like the rubber band snapping back into its normal shape.

You can't discuss this with me, for two very good reasons: 1. You don't know the first thing you're talking about 2. The only way you know how to express your views is to insult those who think differently If you never say anything intelligent (and you don't), it'd be foolish to expect an intelligent discussion. Nonetheless, I've intelligently discussed regression toward the mean; which you were apparently too stupid to understand. So I provided links, which you either didn't read, or read and didn't understand. Then, because I fail to hack a path through the jungle of your own willful stupidity, you start throwing insults at me. The fact I vanished for a while was because I'd found better ways to spend my time than wasting it on someone like you.

Before posting again, you need to go here to educate yourself a little.

The tax break could consist of a lump sum, or a percentage of total taxes owed; with the woman choosing whichever was more beneficial. I realize it's a pretty big tax break right there, but the Bill Joys and Steve Wozniaks of the world create a lot of jobs and wealth. It's worth spending some money to have more people like that. The idea that woman would be receiving only 5th grade educations is yours, not mine. I wonder why you seem to think that the people working in health clinics under my plan would or should be different than those who work in health clinics right now.

Wraith came up with the stretching of the rubber band as a metaphor with which to explain regression toward the mean. Neither he nor I feel measurement error can cause a rubber band to stretch in the literal sense of the word.

A good article. I hope that the cost of solar does end up getting cut in half.

Measurement error causes a distribution to appear to be more spread out than it really is. For example, consider an I.Q. test which gives the correct result 60% of the time, gives a result 10 points too high 20% of the time, and a result 10 points too low 20% of the time. Apply this I.Q. test to a population with 10 people of an I.Q. of 190, 100 people with an I.Q. of 180, 1000 people of an I.Q. of 170, etc. Of the 10 people with an I.Q. of 190, two will get lucky on the I.Q. test and score a 200. Another six will get a 190 on the test, and they'll be joined by 20 people of I.Q. of 180 who got lucky on the test. The true distribution has 0 200s, and 10 190s. But on the I.Q. test, 2 people scored a 200, and 26 scored a 190. Measurement error caused the rubber band to stretch. If you ask those who scored a 200 to retake the test, their expected score the second time around is 190. Remeasuring causes the rubber band to snap back into place.

Sounds fair to me.

I'd determine intelligence through standardized aptitude tests. Melinda Gates would be given tax incentives to have more children. Less wealthy intelligent women would be given subsidies to have children. Existing health clinics could be equipped to provide sterilizations for less intelligent women. The infrastructure is already in place; it just needs to be put to work.

The only thing a textbook won't confirm is your idiotic notion of "regression toward the mean of error."

He used the analogy of stretching a rubber band. Measurement error causes the rubber band to stretch, and remeasuring causes it to snap back into place. He also felt I was saying the same thing in my examples as he was saying with his rubber band metaphor. It's true Wraith initially raised objections to my Monte Carlo simulation. He later wrote that I'd responded publicly and effectively to those objections. Once he understood what I was actually doing with the simulation, his opposition vanished. The more Wraith understood what we were arguing about, the more strongly he sided with me. You're focusing on his earlier posts, back before he'd realized how truly ignorant you were about regression toward the mean.

Nice way to weasel out of the question. Suppose 1000 people had scored a 140 on the test. Of those 1000, you'd randomly choose 100 to retake the test. I can see why you're afraid to answer this question. If I'd committed myself to an erroneous view as strongly as you did, I'd be afraid of being too specific myself.

Suppose you were to take a very large random sample of people, and have them all take I.Q. tests. Randomly choose 100 people who got a 140 on the test, and have them retake it. I contend that the expected average score for those 100 people on the retake will be less than 140. Do you agree or disagree?

At first, he did say I was wrong. He didn't realize what it was we were debating, and thought you guys were attacking the periphery of what I was saying. It took him a while to realize that people like you and Ramius were actually disagreeing with the core of my explanation of regression toward the mean. Once it finally dawned on him that people with your credentials were being so monumentally stupid, he came to my defense.

You're wrong. The only scientific basis a eugenics program requires is for intelligence to be at least partially genetic. Those who would deny genetic influence on intelligence are political idealogues with no credibility whatsoever. You did receive an answer, you just don't remember it. The government should provide intelligent women with financial incentives to have more kids; while also providing less intelligent women with financial incentives to obtain sterilizations. It's stuff like this which leads me to dislike you. Wraith never defended my misremembered formula. He defended my (correct) discussion of regression toward the mean. In case his defense wasn't enough, I've provided a number of links to credible sources which support the way I've described regression toward the mean. In searching for those links, I didn't come across anyone who supported Bungee Jumper's strange view of the matter. If I'm ignoring published scientists, it's because they're ignoring the truth.

You're confusing two very distinct issues. FDR imposed an oil embargo on Japan, he began doubling the size of the U.S. Pacific fleet, and he moved the Pacific Fleet's center of operations from California to Hawaii. There's nothing "wacko" in suggesting that FDR's behavior towards Japan wasn't provocative. On the contrary, to suggest otherwise displays profound historical ignorance. The question of whether FDR knew about Pearl Harbor in advance isn't one I've investigated in great detail, but I'm certainly unaware of any smoking gun to prove he did know.