DC Tom Posted March 9, 2007 Share Posted March 9, 2007 And yes, the element of random chance for an I.Q. test does represent measurement error. And THAT is the crux of your misunderstanding. They're two different things. If you completely eliminate error from an IQ test and make it 100% accurate, one person will score the same score every time they take the test. In that case, the effect you're describing (which you're mistakenly attributing to variance in the population distribution) disappears completely. However, if, using the same test, two parents have a child, the child's IQ will tend to be closer to the population mean, because the variance within the statistical distribution of the IQ scores and the correlation of less than one between parent and child scores means that the scores of successive generations will regress toward the mean, even in the complete absence of error. This demonstrates two things: 1) the INEQUIVALENCE of a test-retest and a parent-child relationship. 2) that ERROR AND VARIANCE ARE TWO DIFFERENT THINGS, AND DIFFERENT THINGS ARE NOT THE SAME. This, if you had ANY sense whatsoever, would be the end of the argument. You don't even have to admit you're wrong, just shut the !@#$ up already. Link to comment Share on other sites More sharing options...
DC Tom Posted March 9, 2007 Share Posted March 9, 2007 Except that, based on my lack of respect for some of the people on here, I do feel it could carry over into the hiring process. And I don't want to do that to my fellow graduates. Not a worry. I don't think any of us own a franchise. Link to comment Share on other sites More sharing options...
Orton's Arm Posted March 9, 2007 Author Share Posted March 9, 2007 Carry over to the hiring process?!? OMG that is effin lame Whatever dude. Someone made the mistake of giving GG hiring authority, and he and I aren't exactly on each other's Christmas card lists. I honestly don't believe he'd hire a graduate from my school if other qualified applicants were available. Link to comment Share on other sites More sharing options...
EC-Bills Posted March 9, 2007 Share Posted March 9, 2007 Whatever dude. Someone made the mistake of giving GG hiring authority, and he and I aren't exactly on each other's Christmas card lists. I honestly don't believe he'd hire a graduate from my school if other qualified applicants were available. You're worried because some random employer might see where you went to school on this board and *not* hire others because of you went to the same school? Link to comment Share on other sites More sharing options...
DC Tom Posted March 9, 2007 Share Posted March 9, 2007 You're worried because some random employer might see where you went to school on this board and *not* hire others because of you went to the same school? I'm pretty sure the only one with that warped a thought process is Holcomb's Arm himself. Maybe he's worried about divulging to himself where he went to school, lest he won't hire any of his classmates. You know, HA...I wouldn't worry about. I'm pretty sure no one here is under the impression that you represent your school's best. Someone has to graduate last in their class. Link to comment Share on other sites More sharing options...
ieatcrayonz Posted March 9, 2007 Share Posted March 9, 2007 I went to one of the top High Schools in my state. Link to comment Share on other sites More sharing options...
Orton's Arm Posted March 9, 2007 Author Share Posted March 9, 2007 And THAT is the crux of your misunderstanding. They're two different things. If you completely eliminate error from an IQ test and make it 100% accurate, one person will score the same score every time they take the test. In that case, the effect you're describing (which you're mistakenly attributing to variance in the population distribution) disappears completely. However, if, using the same test, two parents have a child, the child's IQ will tend to be closer to the population mean, because the variance within the statistical distribution of the IQ scores and the correlation of less than one between parent and child scores means that the scores of successive generations will regress toward the mean, even in the complete absence of error. This demonstrates two things: 1) the INEQUIVALENCE of a test-retest and a parent-child relationship. 2) that ERROR AND VARIANCE ARE TWO DIFFERENT THINGS, AND DIFFERENT THINGS ARE NOT THE SAME. This, if you had ANY sense whatsoever, would be the end of the argument. You don't even have to admit you're wrong, just shut the !@#$ up already. If you'd bothered to read my earlier long post, you could have avoided the above mischaracterizations of my views. Assuming, of course, that being even the slightest bit accurate about my views matters to you. (Does it?) I never attributed the test/retest phenomenon to variance in the population distribution. Where on earth you came up with that idea beats me. I did, however, point out that if you take a collection of people who scored a 140 on an I.Q. test, their scores will, on average, overstate their actual level of intelligence. This is because there are more 130s available for getting lucky, than there are 150s available for getting unlucky. If you were to retest these people, the group's average score on the retest would be, say, 135. So even if I.Q. was 100% narrow-sense heritable, you wouldn't expect these people's children to have average scores of 140 on an I.Q. test. They should expect an average of 135, because that's what their parents would get on the retest. Let's say the children averaged a 130 on the test. Of those ten points of difference, five are due to the parents having gotten lucky on the test, and five are due to children's actual I.Q.s moving toward the population's mean. Link to comment Share on other sites More sharing options...
Ramius Posted March 9, 2007 Share Posted March 9, 2007 You're worried because some random employer might see where you went to school on this board and *not* hire others because of you went to the same school? Lets toss insecurities and personal inadequacies on top of his inability to comprehend math and biology and economics. Link to comment Share on other sites More sharing options...
DC Tom Posted March 9, 2007 Share Posted March 9, 2007 I never attributed the test/retest phenomenon to variance in the population distribution. Where on earth you came up with that idea beats me. No, you're attributing variance in the population distribution to error in the test, you moron. If you remove the error, you still have variance in the population distribution - and hence regression toward the mean - BECAUSE IT HAS NOTHING TO DO WITH ERROR. blather That's not even right. How you can't see that's not even right is beyond me. Let's say the children averaged a 130 on the test. Of those ten points of difference, five are due to the parents having gotten lucky on the test, and five are due to children's actual I.Q.s moving toward the population's mean. So if the child regresses toward the mean from the parents' tests, it's the parents' fault for being lucky. Like I said, no sense... Link to comment Share on other sites More sharing options...
Ramius Posted March 9, 2007 Share Posted March 9, 2007 No, you're attributing variance in the population distribution to error in the test, you moron. If you remove the error, you still have variance in the population distribution - and hence regression toward the mean - BECAUSE IT HAS NOTHING TO DO WITH ERROR. That's not even right. How you can't see that's not even right is beyond me. So if the child regresses toward the mean from the parents' tests, it's the parents' fault for being lucky. Like I said, no sense... If children are going to ultimately regress to the mean, how is a eugenics program supposed to work? Link to comment Share on other sites More sharing options...
DC Tom Posted March 9, 2007 Share Posted March 9, 2007 If children are going to ultimately regress to the mean, how is a eugenics program supposed to work? Or, if you consistently overestimate the parents' IQs, how are you going to choose your breeding stock? He's constructed a breeding program where there's no regression toward the mean, just an inability to measure the very qualifications you need for your breeding program. I guess in that respect he's WORSE than Nazis. They're both crackpots...but at least the Nazis were crackpots with established objective measures. Link to comment Share on other sites More sharing options...
Orton's Arm Posted March 9, 2007 Author Share Posted March 9, 2007 You're worried because some random employer might see where you went to school on this board and *not* hire others because of you went to the same school? To be honest, I don't know much about the people on here--certainly not enough to make a comprehensive list of the people with hiring authority. And what little I know about Ramius, or Bungee Jumper, or GG, or Coli, is a lot more bad than good. And you're asking me to trust these people with information that could be used to hurt my classmates? - What do you think that Bungee Jumper or Ramius have done to have earned that trust? - What's my incentive for providing these people with additional information? They've consistently abused what I've already given them. Why should I trust them with more? I don't want to make any mystery of things. It's a top 50-school. Just make a list of the 50 best schools in the country, eliminate the MITs and the Harvards from the list, and pick a name at random from what's left. The school you pick probably won't be a whole lot different from my alma mater. Link to comment Share on other sites More sharing options...
DC Tom Posted March 9, 2007 Share Posted March 9, 2007 To be honest, I don't know much about the people on here--certainly not enough to make a comprehensive list of the people with hiring authority. And what little I know about Ramius, or Bungee Jumper, or GG, or Coli, is a lot more bad than good. And you're asking me to trust these people with information that could be used to hurt my classmates? - What do you think that Bungee Jumper or Ramius have done to have earned that trust? - What's my incentive for providing these people with additional information? They've consistently abused what I've already given them. Why should I trust them with more? I don't want to make any mystery of things. It's a top 50-school. Just make a list of the 50 best schools in the country, eliminate the MITs and the Harvards from the list, and pick a name at random from what's left. The school you pick probably won't be a whole lot different from my alma mater. ...of course, you'll most likely be wrong, but if you pick again the error will cause you to regress toward the correct school... Link to comment Share on other sites More sharing options...
Alaska Darin Posted March 9, 2007 Share Posted March 9, 2007 To be honest, I don't know much about the people on here--certainly not enough to make a comprehensive list of the people with hiring authority. And what little I know about Ramius, or Bungee Jumper, or GG, or Coli, is a lot more bad than good. And you're asking me to trust these people with information that could be used to hurt my classmates? - What do you think that Bungee Jumper or Ramius have done to have earned that trust? - What's my incentive for providing these people with additional information? They've consistently abused what I've already given them. Why should I trust them with more? I don't want to make any mystery of things. It's a top 50-school. Just make a list of the 50 best schools in the country, eliminate the MITs and the Harvards from the list, and pick a name at random from what's left. The school you pick probably won't be a whole lot different from my alma mater. Introspection. It's not just a word in the dictionary. Link to comment Share on other sites More sharing options...
ieatcrayonz Posted March 9, 2007 Share Posted March 9, 2007 Introspection. It's not just a word in the dictionary. That may be the corniest point anyone has ever made here. Link to comment Share on other sites More sharing options...
Orton's Arm Posted March 9, 2007 Author Share Posted March 9, 2007 More inability to comprehend arguments that ought to be obvious to any adult with at least an average level of intelligence. Conduct a study about the children of really smart people. First you have to define really smart people. You give the entire population an I.Q. test, and you choose parents who scored a 140. But as I've spent the last 60+ pages establishing, those who obtain extreme scores on an error-prone test are generally somewhat closer to the population's mean than their test scores indicate. Even if the children have the same underlying I.Q.s as their parents, the children's measured I.Q.s will be closer to the population's mean. The parents, as a group, will have gotten slightly lucky on the I.Q. test, because they were selected on the basis of their test scores, and a small but significant portion of that test score is based on luck. The children, on the other hand, are expected to be luck neutral on the test. So if children score a little less well than their intelligent parents, at least some of this is due to the test/retest phenomenon. Link to comment Share on other sites More sharing options...
ieatcrayonz Posted March 9, 2007 Share Posted March 9, 2007 To be honest, I don't know much about the people on here--certainly not enough to make a comprehensive list of the people with hiring authority. And what little I know about Ramius, or Bungee Jumper, or GG, or Coli, is a lot more bad than good. And you're asking me to trust these people with information that could be used to hurt my classmates? - What do you think that Bungee Jumper or Ramius have done to have earned that trust? - What's my incentive for providing these people with additional information? They've consistently abused what I've already given them. Why should I trust them with more? I don't want to make any mystery of things. It's a top 50-school. Just make a list of the 50 best schools in the country, eliminate the MITs and the Harvards from the list, and pick a name at random from what's left. The school you pick probably won't be a whole lot different from my alma mater. I want to give this a shot. I keep information about women that very few have. Can you estimate what percentage of chicks at your school are Orwellian? If your estimate is close I promise I will guess the school. Link to comment Share on other sites More sharing options...
DC Tom Posted March 9, 2007 Share Posted March 9, 2007 Big whoop if we make fun of it. You know what? If it makes you feel better, you can pick on my alma mater, the University of Illinois. Good school. Top-5 milkshake program. Link to comment Share on other sites More sharing options...
DC Tom Posted March 9, 2007 Share Posted March 9, 2007 Conduct a study about the children of really smart people. First you have to define really smart people. You give the entire population an I.Q. test, and you choose parents who scored a 140. But as I've spent the last 60+ pages establishing, those who obtain extreme scores on an error-prone test are generally somewhat closer to the population's mean than their test scores indicate. Even if the children have the same underlying I.Q.s as their parents, the children's measured I.Q.s will be closer to the population's mean. The parents, as a group, will have gotten slightly lucky on the I.Q. test, because they were selected on the basis of their test scores, and a small but significant portion of that test score is based on luck. The children, on the other hand, are expected to be luck neutral on the test. So if children score a little less well than their intelligent parents, at least some of this is due to the test/retest phenomenon. Never mind that an equal proportion of people score less than their true score, and thus the effect of error zeros out over the entire population, which completely nullifies your argument anyway...YOU'RE NOT RETESTING THE PARENTS WHEN YOU TEST THE CHILD. You truly are a glutton for punishment. Link to comment Share on other sites More sharing options...
GG Posted March 9, 2007 Share Posted March 9, 2007 I don't want to make any mystery of things. It's a top 50-school. Just make a list of the 50 best schools in the country, eliminate the MITs and the Harvards from the list, and pick a name at random from what's left. The school you pick probably won't be a whole lot different from my alma mater. I'm guessing if you eliminate the MITs & Harvards, you're left with Kean University? Link to comment Share on other sites More sharing options...
Recommended Posts