Regression toward the mean

[Orton's Arm]

So we're all the way back to "error causes regression toward the mean"...but with a twist, that the parent's error causes the children's regression toward the mean. 

 

Which once again demonstrates: you can't tell the difference between error and normal population variance. 

864272[/snapback]

In this discussion, your attempts at rebuttals have never been particularly strong. But this is one of the weakest ones yet.

 

One of the interesting things about the phenomenon I'm describing is that it works the other way too. Suppose you were to select children with the highest I.Q. scores. On average, their parents will tend to have somewhat lower scores. Why? Because in selecting children with the highest scores, you selected a group that was disproportionately lucky on the test. Their parents were, on average, luck-neutral; and hence obtained somewhat lower scores.

[Taro T]

So we're all the way back to "error causes regression toward the mean"...but with a twist, that the parent's error causes the children's regression toward the mean. 

 

Which once again demonstrates: you can't tell the difference between error and normal population variance. 

864272[/snapback]

Well, if the parents had been able to work one of those Trojan thingies the children wouldn't be around, so it has to be the parents' error that is causing the children's apparent regression toward the mean.

 

I'm sure I'm going to need much more of before this chain of threads die their merciful death.

[Orton's Arm]

Well, if the parents had been able to work one of those Trojan thingies the children wouldn't be around, so it has to be the parents' error that is causing the children's apparent regression toward the mean. 

 

I'm sure I'm going to need much more of      before this chain of  threads die their merciful death.

864289[/snapback]

Merciful death? Are you kidding me? Every football discussion board should have its own politics section. Every politics section needs at least a ten page thread on regression toward the mean.

[Taro T]

In this discussion, your attempts at rebuttals have never been particularly strong. But this is one of the weakest ones yet.

 

One of the interesting things about the phenomenon I'm describing is that it works the other way too. Suppose you were to select children with the highest I.Q. scores. On average, their parents will tend to have somewhat lower scores. Why? Because in selecting children with the highest scores, you selected a group that was disproportionately lucky on the test. Their parents were, on average, luck-neutral; and hence obtained somewhat lower scores.

864280[/snapback]

The parents' scores differing from the children's scores is not due to luck. It is a reflection of an expected correlation between the scores of close to but less than 1.0 and the variance within the population.

 

 

 

 

Just when I think I'm out, I get dragged back again.

[Bungee Jumper]

One of the interesting things about the phenomenon I'm describing is that it works the other way too. Suppose you were to select children with the highest I.Q. scores. On average, their parents will tend to have somewhat lower scores. Why? Because in selecting children with the highest scores, you selected a group that was disproportionately lucky on the test. Their parents were, on average, luck-neutral; and hence obtained somewhat lower scores.

864280[/snapback]

 

Now error causes regression from the mean?

 

This is why I keep this up. Every time I think your idiocy's peaked, you come up with something even stupider.

[Bungee Jumper]

The parents' scores differing from the children's scores is not due to luck.  It is a reflection of an expected correlation between the scores of close to but less than 1.0 and the variance within the population.

864300[/snapback]

 

Actually, the correlation between parents' and childrens' scores is much less than 1. Which is why regression toward the mean happens.

 

Which must mean that a correlation of less than 1 is error...

[Taro T]

Actually, the correlation between parents' and childrens' scores is much less than 1.  Which is why regression toward the mean happens. 

 

Which must mean that a correlation of less than 1 is error... 

864314[/snapback]

I will take your word for it that the correlation between the 2 is significantly lower. My bad. I made an assumption off the word "somewhat". (A rather poor assumption, it would appear.)

 

Out of curiosity, (because at this moment I don't have time to try to track it down although I'm pretty sure links to it have been posted somewhere in 1 of the 30 threads on this subject, sorry) do you know off hand what a typical parent - child IQ correlation is or what range is typical?

[Orton's Arm]

Now error causes regression from the mean? 

 

This is why I keep this up.  Every time I think your idiocy's peaked, you come up with something even stupider.

864310[/snapback]

Wrong from start to finish. This isn't something I "came up with." It's an observation of fact.

 

Do the math. Create a Gaussian population. Give each member an I.Q. test, with a normally distributed error term with a mean of zero. Select out some subset of the population that did the best on the first test, and have them retested. Compare the group's average score for the first test, versus the second one.

 

Any time you select a group of people who did the best on an I.Q. test, you're selecting a group that's disproportionately lucky on that test. The parents or children of this group will, on average, have been luck-neutral on the test; and will have had lower I.Q. scores.

[Bungee Jumper]

I will take your word for it that the correlation between the 2 is significantly lower.  My bad.  I made an assumption off the word "somewhat".  (A rather poor assumption, it would appear.)     

 

Out of curiosity, (because at this moment I don't have time to try to track it down although I'm pretty sure links to it have been posted somewhere in 1 of the 30 threads on this subject, sorry) do you know off hand what a typical parent - child IQ correlation is or what range is typical?

864326[/snapback]

 

Offhand...I think it's about .4.

 

HA thinks it's .8, because the heritability of intelligence in adults is estimated to be about .8. Of course, he doesn't know what heritability is...or correlation is...or what a parent-child relationship is, apparently...but other than that he's still completely wrong.

[Bungee Jumper]

Wrong from start to finish. This isn't something I "came up with." It's an observation of fact.

 

Do the math. Create a Gaussian population. Give each member an I.Q. test, with a normally distributed error term with a mean of zero. Select out some subset of the population that did the best on the first test, and have them retested. Compare the group's average score for the first test, versus the second one.

 

Any time you select a group of people who did the best on an I.Q. test, you're selecting a group that's disproportionately lucky on that test. The parents or children of this group will, on average, have been luck-neutral on the test; and will have had lower I.Q. scores.

864328[/snapback]

 

And once again, you're confusing error with population variance.

 

Will you ever stop confusing those?

[Orton's Arm]

I will take your word for it that the correlation between the 2 is significantly lower.  My bad.  I made an assumption off the word "somewhat".  (A rather poor assumption, it would appear.)     

 

Out of curiosity, (because at this moment I don't have time to try to track it down although I'm pretty sure links to it have been posted somewhere in 1 of the 30 threads on this subject, sorry) do you know off hand what a typical parent - child IQ correlation is or what range is typical?

864326[/snapback]

The correlation between parents' and childrens' I.Q.s is around 0.75; and it goes up as children get older. The correlation between a person's score between different I.Q. tests is somewhere between 0.8 and 0.9 (I don't remember where, specifically.)

[Orton's Arm]

Offhand...I think it's about .4. 

 

HA thinks it's .8, because the heritability of intelligence in adults is estimated to be about .8.  Of course, he doesn't know what heritability is...or correlation is...or what a parent-child relationship is, apparently...but other than that he's still completely wrong.

864330[/snapback]

We've already had the "heritability" debate, which I won hands-down. Why you insist on bringing it up again is beyond me.

[Bungee Jumper]

The correlation between parents' and childrens' I.Q.s is around 0.75; and it goes up as children get older.

864332[/snapback]

 

[Bungee Jumper]

We've already had the "heritability" debate, which I won hands-down. Why you insist on bringing it up again is beyond me.

864334[/snapback]

 

Ever notice how you're the only one thinking you're winning any debates?

 

So clearly the problem is with everyone else...

[Orton's Arm]

Ever notice how you're the only one thinking you're winning any debates? 

 

So clearly the problem is with everyone else... 

864338[/snapback]

I don't "think" I won the heritability debate. I know I won that debate. First, I showed you a website which gave specific, mathematical definitions of the word. The definition you were using was capital H^2. The definition I was using was lower-case h^2. When the American Psychological Association declared that heritability for intelligence was about 0.75, they specifically said that by "heritability" they meant lower-case h^2.

 

I couldn't possibly have asked for a more clear-cut victory.

[Ramius]

Any time you select a group of people who did the best on an I.Q. test, you're selecting a group that's disproportionately lucky on that test. The parents or children of this group will, on average, have been luck-neutral on the test; and will have had lower I.Q. scores.

864328[/snapback]

 

Ahhh, you've made it much more clearer.

 

Only parents can get lucky on this P.O.S. you call a statistical analysis. When the parents have kids, the kids wont get lucky on the test.

[EC-Bills]

Merciful death? Are you kidding me? Every football discussion board should have its own politics section. Every politics section needs at least a ten page thread on regression toward the mean.

864296[/snapback]

[Ramius]

We've already had the "heritability" debate, which I won hands-down.

864334[/snapback]

 

 

Thats the best line you have yet. You cant even distinguish between heritability and inheritability, or even define heritability for that matter. And you claim you "won" the debate.

 

How's the weather in your little world where you're always right and everyone else is wrong?

[Ramius]

I don't "think" I won the heritability debate. I know I won that debate.

864368[/snapback]

 

 

The only thing funnier than this post would be seeing an actual PHOTO of you.

[Bungee Jumper]

I don't "think" I won the heritability debate. I know I won that debate. First, I showed you a website which gave specific, mathematical definitions of the word. The definition you were using was capital H^2. The definition I was using was lower-case h^2. When the American Psychological Association declared that heritability for intelligence was about 0.75, they specifically said that by "heritability" they meant lower-case h^2.

 

I couldn't possibly have asked for a more clear-cut victory.

864368[/snapback]

 

None of which actually says anything about what heritability actually is.

 

You have a real talent for recall. Really. I'm serious. You've expressed a truly startling number of concepts in this debate. Too bad you have absolutely no understanding of any of them, and can't put them together into anything resembling a coherent statement.