GG Posted November 8, 2006 Share Posted November 8, 2006 In his defense (don't ask me why I'm defending him, I don't !@#$ing know), 115 would be 1.5 standard deviations away from the mean, which would mean he's safely selecting from within the "gifted" category. 829093[/snapback] Wouldn't truly gifted be >2 standard deviations away? Which is another way of saying he's picking numbers out of his... head? Link to comment Share on other sites More sharing options...
Orton's Arm Posted November 8, 2006 Share Posted November 8, 2006 That makes no sense. I'm not surprised, because it's you after all. But it makes no sense. You're using a defined normally distributed error to prove the error's not normally distributed. That is all kinds of !@#$ing stupid. 829071[/snapback] Thanks for addressing GG's objection. Now for my response to your post. To show how measurement error can affect your perception of a population, consider a population group that contains the following people: 10 people with I.Q.s of 190, 100 people with I.Q.s of 180, 1000 people with I.Q.s of 170, etc. A population like this looks vaguely like the right hand tail of that bell curve--enough like it to illustrate my point. Suppose you were to give each person an I.Q. test. A person taking the test has a 60% chance of getting the right score, a 20% chance of getting lucky with a score that's 10 points too high, and a 20% chance of getting unlucky with a score that's 10 points too low. How will the measured I.Q. scores compare to the true I.Q. values? First, let's look at the 190s: 2 will get lucky and score 200 on the test. Another 6 will score 190, and the remaining 2 will be unlucky and score 180. Based on measured I.Q.s, one would conclude that there are two people in this population group with I.Q.s of 200. In fact there are zero. Of the 100 people with an I.Q. of 180, 20 will get lucky and score a 190. Add those 20 to the six 190s who actually scored a 190, and there are 26 people with a measured I.Q. of 190. The true population only has ten such people; so once again measurement error has led to an overestimate of the number of people in the far right tail. The group with a measured I.Q. of 200 has a real I.Q. of only 190. The people who scored a 190 on the test, on average, have real I.Q.s that aren't much above 180. If you were to ask the people who scored a 200 on the test to retake it, their true I.Q. of 190 would manifest itself. Likewise, if those who scored a 190 were asked to retake the test, their scores the second time around would, on average, be closer to 180 than 190. My simulation modeled this same phenomenon using a normally distributed population and a normally distributed error term for both test takings. Link to comment Share on other sites More sharing options...
Bungee Jumper Posted November 8, 2006 Share Posted November 8, 2006 Wouldn't truly gifted be >2 standard deviations away? Which is another way of saying he's picking numbers out of his... head? 829119[/snapback] Gifted is 1 SD. Genius is 2 SD. Average is just error. And yes, he's picking numbers out of his...ass. I'm convinced he hit on a reasonably correct 1.5 standard deviations off the mean simply by accident, as there's no WAY he used any sort of discretion or judgement in choosing it. Link to comment Share on other sites More sharing options...
Bungee Jumper Posted November 8, 2006 Share Posted November 8, 2006 Likewise, if those who scored a 190 were asked to retake the test, their scores the second time around would, on average, be closer to 180 than 190. 829161[/snapback] And here's where I start laughing my ass off. How does the error just go away the second time around? If the take the test again, you still have 10 people with a "real IQ" (which is a total bull sh-- term, by the way ) of 190 taking the same test with the same error...which means you get 2 people scoring 200, and your distribution's the same. You can't just magically eliminate the error. Well, you can, apparently. But people with a modicum of common sense and bound by reality can't... Link to comment Share on other sites More sharing options...
meazza Posted November 8, 2006 Share Posted November 8, 2006 And here's where I start laughing my ass off. How does the error just go away the second time around? If the take the test again, you still have 10 people with a "real IQ" (which is a total bull sh-- term, by the way ) of 190 taking the same test with the same error...which means you get 2 people scoring 200, and your distribution's the same. You can't just magically eliminate the error. Well, you can, apparently. But people with a modicum of common sense and bound by reality can't... 829438[/snapback] You obviously don't know your statistics. Stick to your physics Tom Link to comment Share on other sites More sharing options...
Bungee Jumper Posted November 8, 2006 Share Posted November 8, 2006 You obviously don't know your statistics. Stick to your physics Tom 829442[/snapback] My statistical physics? Link to comment Share on other sites More sharing options...
meazza Posted November 8, 2006 Share Posted November 8, 2006 My statistical physics? 829447[/snapback] Whatever you want to call it Link to comment Share on other sites More sharing options...
Pine Barrens Mafia Posted November 8, 2006 Share Posted November 8, 2006 I smell a telephone pole... Link to comment Share on other sites More sharing options...
meazza Posted November 8, 2006 Share Posted November 8, 2006 I smell a telephone pole... 829482[/snapback] I smell someone as intelligent as a telephone pole. Link to comment Share on other sites More sharing options...
Ramius Posted November 8, 2006 Share Posted November 8, 2006 And here's where I start laughing my ass off. How does the error just go away the second time around? If the take the test again, you still have 10 people with a "real IQ" (which is a total bull sh-- term, by the way ) of 190 taking the same test with the same error...which means you get 2 people scoring 200, and your distribution's the same. You can't just magically eliminate the error. Well, you can, apparently. But people with a modicum of common sense and bound by reality can't... 829438[/snapback] I've been trying to figure this out for 15 pages myself. How in sam hell does someone automatically do worse on the second IQ test, and how does error automatically disappear on the second test. Where does it go? So lets say i take the IQ test the first time and score 190. the second time i am have no chance of scoring higher? I automatically score lower? wtf? So summing this bull sh-- up, HA is trying to state that error causes regression toward the mean, and that this error automatically ceases to exist in the second test? What kind of ass backwards logic is that? what kind fo retard comes up with that? Link to comment Share on other sites More sharing options...
Bungee Jumper Posted November 8, 2006 Share Posted November 8, 2006 So lets say i take the IQ test the first time and score 190. the second time i am have no chance of scoring higher? I automatically score lower? wtf? 829505[/snapback] No, if you take the IQ test the first time and score 190, and your "real IQ" is 180, and the error is +/- 10, you have to score lower the second time. The real question then becomes: how do you determine your "real IQ"? I'm sure the answer will be something like "Your real IQ is the number it regresses to after successive testing." Which just demonstrates my initial point: he's measuring the wrong !@#$ing thing! The IQ measurement isn't what's regressing, the error is regressing toward the mean error of zero. Link to comment Share on other sites More sharing options...
Pine Barrens Mafia Posted November 8, 2006 Share Posted November 8, 2006 I smell someone as intelligent as a telephone pole. 829490[/snapback] You really should shower more often. Link to comment Share on other sites More sharing options...
meazza Posted November 8, 2006 Share Posted November 8, 2006 You really should shower more often. 829546[/snapback] Really... Really Lame. I expect more from you. Link to comment Share on other sites More sharing options...
Pine Barrens Mafia Posted November 8, 2006 Share Posted November 8, 2006 Really... Really Lame. I expect more from you. 829549[/snapback] I'm honored, really. Link to comment Share on other sites More sharing options...
meazza Posted November 8, 2006 Share Posted November 8, 2006 I'm honored, really. 829553[/snapback] Ok stop being a B word. I'm sorry for calling you a retard. Link to comment Share on other sites More sharing options...
Bungee Jumper Posted November 8, 2006 Share Posted November 8, 2006 Ok stop being a B word. I'm sorry for calling you a retard. 829557[/snapback] Why? He is a retard. Link to comment Share on other sites More sharing options...
Pine Barrens Mafia Posted November 8, 2006 Share Posted November 8, 2006 Why? He is a retard. 829574[/snapback] Link to comment Share on other sites More sharing options...
meazza Posted November 8, 2006 Share Posted November 8, 2006 Why? He is a retard. 829574[/snapback] Nah that's harsh. I don't have a mean bone in my body. Link to comment Share on other sites More sharing options...
Bungee Jumper Posted November 8, 2006 Share Posted November 8, 2006 Nah that's harsh. I don't have a mean bone in my body. 829578[/snapback] If you ask him nicely, Ed can probably help with that... Link to comment Share on other sites More sharing options...
meazza Posted November 8, 2006 Share Posted November 8, 2006 If you ask him nicely, Ed can probably help with that... 829590[/snapback] Whoa there. Link to comment Share on other sites More sharing options...
Recommended Posts