Tuesday, September 14, 2010

More on psychometrics

I've had some email discussions elaborating on the psychometrics slides I posted earlier. The slides themselves don't convey a lot of the important points I made in the talks so I thought I'd share this message on the blog.

Hi Guys,

I'm very interested in exactly the question Henry is getting at.

I think our simple two factor model

Grades = ability + work ethic = IQ + W

is not too crazy. Note that once you fix the ability level (=SAT score) the remaining variance in GPA has about the same SD regardless of value of SAT score (vertical red lines in the big figure in the slides). That suggests that we can think of IQ and W as largely uncorrelated random variables -- so there are smart lazy people, hard working dumb people, etc. I can't really prove the residual variance after IQ is controlled for is due to work ethic, but my experience in the classroom suggests that it is. (Note work ethic here isn't necessary general work ethic as a personality factor, but how hard the kid worked in the specific course. However, in our data we average over many courses taken by many kids, so perhaps it does get at variation of personality factor(s) in the overall population.) Beyond work ethic, some people are just more "effective" -- they can get themselves organized, are disciplined, can adapt to new challenges, are emotionally robust -- and this is also absorbed in the W factor above.

Now, in some fields there seems to be a minimum cognitive threshold. I've known physics students who worked incredibly hard and just couldn't master the material. That is reflected in our data on pure math and physics majors at UO. For all majors there is a significant positive correlation between SAT and upper GPA (in the range .3-.5).

Whether IQ has a large impact on life outcomes depends on how you ask the question. I do believe that certain professions are almost off-limits for people below a certain IQ threshold. But for most jobs (even engineer or doctor), this threshold is surprisingly low IF the person has a strong work ethic. In other words a +1 SD IQ person can probably still be a doctor or engineer if they have +(2-3) SD work ethic. However, such people, if they are honest with themselves, understand that they have some cognitive disadvantages relative to their peers. I've chosen a profession in which, every so often, I am the dumbest guy in the room -- in fact I put myself in this situation by going to workshops and wanting to talk to the smartest guys I can find :-) For someone of *average* work ethic I think you can easily find jobs for which the IQ threshold is +2 SD or higher. The typical kid admitted to grad school in my middle-tier physics department is probably > +2 SD IQ and at least +1.5 SD in work ethic -- ditto for a top tier law or med school. That's probably also the case these days for any "academic admit" at a top Ivy.

For typical jobs I think the correlation between success/income and IQ isn't very high. Other factors come into play, like work ethic, interpersonal skills, affect, charisma, luck, etc. This may even be true in many "elite" professions once you are talking about a population where everyone is above the minimum IQ threshold -- if returns to IQ above threshold are not that large then the other factors dominate and determine level of success. What is interesting about the Roe and SMPY studies is that they suggest that in science the returns to IQ above the +2 SD threshold (for getting a PhD) are pretty high. ***

Henry is right that for ideological reasons many researchers are happy to present the data so as to minimize the utility of IQ or testing in making life predictions. They might even go so far as to claim that since we use g-loaded tests in admissions, the conclusion that some professions require high IQ is actually circular. The social scientist who walked out of my Sci Foo talk actually made that claim.

Finally, when it comes to *individual* success I think most analysts significantly underestimate the role of pure blind luck (i.e., what remains when all other reasonable, roughly measurable variables have been accounted for; of course this averages out of any large population study). Or perhaps I am just reassuring myself about my limited success in life :-)


Steve

PS In the actual talks I gave I made most of these points. The slides are kind of bare bones...


*** You would have difficulty finding a hard scientist who would disagree with the statement it is a big advantage in my field to be super smart. However, thanks to political correctness, social science indoctrination, or unfamiliarity with psychometrics, it IS common for scientists to deny that being super smart has anything to do with scores on IQ tests. I myself question the validity of IQ tests beyond +(3-4) SD -- I'm more impressed by success on the IMO, Putnam, or in other high level competitions. (Although I realize that training has a big impact on performance in these competitions I do think real talent is a necessary condition for success.)

61 comments:

Yan Shen said...

Remember, reasoned discourse is perfectly acceptable as long as it's grounded within the facts. What's not acceptable and beyond the pale of civilized behavior is to racially denigrate other ethnic groups with explicit slurs or to advocate violence against them. What you'll never find me doing is making derogatory remarks about other people or suggesting that they be confronted physically. In this respect, I'm at least a few orders of magnitude above the Steve Sailer white nationalist crowd in terms of civilized behavior.

Anonymous said...

I've never seen Sailer say the things you label here as "white nationalist," but I have seen Dennis Mangan talk about ethnic endangerment and preservation explicitly. Elsewhere in these comments, you seemed to approve of Mangan, though. (I mean no disrespect to Mangan, I find him very insightful.) Do you think it is simply wrong and evil to have any interest in preserving the uniqueness and integrity of one's group? (Except for Jews perhaps, and maybe Chinese, though I am just guessing.)

Also, how do you know influential people don't read his blog? We know for a fact that some do, considering public exchanges he has had in the past. And no where have I seen any suggestion that Sailer does not know that he has a wide range of readers that includes plenty of less intelligent people.

And I don't know, but I find it a bit annoying that you think you have the monopoly on what's "healthy" or "normal" (which you apparently equate with "good").

What I'm trying to do at this point is understand how you came to this view. Steve Sailer doesn't seem disrespectful to East Asians, but on the contrary, merely points out the fact of their above average scores on many tests.

Yan Shen said...

I think it's evil and borderline psychopathic to allow your readers to use explicit racial slurs against other ethnic groups. You may find that sentiment annoying, but I'd glad to educate you on how normal, civilized people behave.

Yan Shen said...

And let's drop the pretense about Sailer being respectful towards East Asians. You must have missed his whining rants about how Asians game the UC admissions system. Apparently when ethnic whites become academically displaced, then all of a sudden meritocracy no longer reigns supreme. But he's more than glad to shit all over blacks and Hispanics though, when arguing about how white academic success relative to blacks and Hispanics should be accepted as the result of free-market meritocracy.

Yan Shen said...

There's nothing wrong with ethnic solidarity. What's wrong is when ethnic solidarity also entails out-group hostilities, including the explicit use of racial slurs or the advocating of violence against other ethnic groups. You'll find both of these things on white nationalist blogs. I could care less if any group of people wants to preserve their own ethnic heritage. What gets me worked up is when people engage in outright bigotry. And if any of that is directed towards me specifically, well, you can be sure that I'll voice my opinions about it.

Anonymous said...

Wow, you clearly are hallucinating. I read those posts, and he never said that East Asians did not already have high enough scores to get a higher admissions rate than others. He was just saying that there were ways of boosting admissions rates, like additional tests, and that East Asians seem to make use of these. He pointed out that white Americans, feeling a part of the system, may be more complacent and do seek advantages as much as they could. Maybe also East Asians value education more. The American education system is very complex with lots of twists and turns. It doesn't always go in the same direction. Sailer even affirmed that East Asians would get in at a higher rate regardless of "gaming." I read these posts in a completely different way from you.

Anonymous said...

Edit: that should be "white Americans, feeling a part of the system, may be more complacent and do *not* seek advantages as much as they could."

Anonymous said...

And if we are all taking the chance to air our grievances, let me have mine.

Mr. Hsu, I don't appreciate your veiled Chinese supremacism one bit! And furthermore, I challenge you to an MMA duel. If I win, then you have to stop being racist in your blog against all non-Chinese. Just kidding, sorry for filling up your blog with this argument, Steve!

Yan Shen said...

If you can find an instance of where Steve Hsu has used a racially derogatory slur against whites or advocated violence against them, you might have an actual point.

Yan Shen said...

Look I don't want to continually bash him here. So let me just summarize my main points and be done with it.

The guy exhibits a paranoid degree of ethnocentrism that probably goes beyond what's normal or healthy. He exercises extremely poor judgment in terms of the kinds of comments that he allows to slip through his moderation. He has this delusional belief that many of the most intelligent and influential people in America read his blog, and that these people are indicative of the average quality of his readership. And last but not least, the guy comes off as just being a complete douchebag in general, someone who seems to lack any normal degree of sociability. I would say that his paranoid out-group hostility verges on the psychopathic. These characterizations also fit most of the white nationalist crowd quite well. Those people seem to have this bizarre notion that there's a widespread conspiracy going on to deracinate native gentile white Americans and that they're somehow in the middle of a cosmic battle to preserve traditional gentile white culture.

Yan Shen said...

I wonder how African Americans would feel if I "playfully" referred to them as the heavyweight title contenders of violent crime.

Yan Shen said...

If you can't detect the obvious degree of sarcasm and animus present in Sailer's comment, perhaps you lack in normal human empathy. I'm not saying those kinds of comments are the worst thing in the world. But he does come off as being somewhat of a douchebag though.

Anonymous said...

First, aggrievement is one of the main ways they silence dissent, so I don't really see that this is inaccurate. In explaining the dynamic, one would naturally talk about the use of aggrievement.

Second, with that statement, you seem to be mistaking merely playful, informal language for "racial slurs." And generalizations should be understood as just that. He's obviously not saying that every single member of these groups behaves that way. This is a blog, not a peer reviewed scientific journal. I don't see any problem here at all. Saying that many people in some groups use "aggrievement" is not even remotely close to what you accuse him of. You seem to be looking really hard to find something that's just not there.

Yan Shen said...

That must be why Sailer sarcastically refers to the Jews and blacks as the reigning heavyweight title contenders of competitive aggrievement. Those comments sound to me to be somewhat mean spirited in nature and intended mostly to egg on the white nationalist audience whom he knows hes pandering to.

http://isteve.blogspot.com/2010/07/joel-steins-own-private-jesse-jackson.html

"Still, the reigning heavyweight title contenders of competitive aggrievement, the blacks and the Jews, should be aware that there's a new Indian kid in town who is ready to rumble."

Reasoned discourse grounded within the facts is perfectly acceptable. Voicing concerns what about Jewish liberals are doing in terms of influencing American public policy is perfectly permissible.

Using explicit racial slurs against other ethnic groups, advocating violence against them, or in the case of Sailer, just being a douchebag in general, probably should be frowned upon.

Anonymous said...

It sounds like you've really spent a lot of time trying to psychoanalyze Steve Sailer. That's interesting. I don't know about him being part Jewish, but it sounds like you've got some kind of "race traitor" notion going. Is it different when a non-Jew talks a lot about Jews? Anyway, and more importantly, it's very easy to understand a disproportionate focus on people of Jewish descent by someone who writes about race and ethnicity.

Jews do hold a lot of high positions and are influential in Western society. If one of the results of that fact is large-scale censorship and marginalization of debate on these issues that Steve finds important, and added to that we have the irony that members of this ethnicity are where they are due to the very variation among humans that they ignore in mainstream publications, then someone who focuses on the issues might want to talk about that. It's natural to be frustrated at the current state of affairs, and it seems to me that Steve Sailer, far from having any malice, is driving more toward changing the view Jews take of themselves in American society to recognize that they are "in" rather than "out" and to take more responsibility for the people whom their decisions and words affect.

ABCD said...

Well, there are innumerable occasions where you're dragged in racial differences (off-topic links, off-topic comments) and then brought in the Asian angle when the discourse didn't revolve around race. While there's no direct denigration, there are subtle ways of doing the same thing ("OMG! Only 8% of blacks score above the Asian median in the XYZ examination").

For an individual who ostensibly believes in the primacy of the individual, you have an unhealthy obession with race.

Yan Shen said...

I often do criticize what Chinese people do. I believe that everyone should engage in a healthy amount of self-criticism from time to time.

However, Steve Sailer's self-flagellation would be the equivalent of me referring to the Chinese as slant eyed chinks, an act of self-hatred which goes above and beyond any degree of normal self-criticism.

Yan Shen said...

I should clarify my previous comment. What you'll never find me doing is making derogatory remarks about another ethnic group as a whole. I will however criticize individuals or a group of individuals if I feel like they deserve to be called out on. So for instance, you'll hear me call a spade a spade and refer to the white nationalist crowd as a group of mostly dim-witted rednecks, because from everything I've experienced, that characterization is remarkably accurate. What you won't see me do is racially denigrate an entire ethnic group, because I almost never view issues through the prism of race. I try to treat people first and foremost as individuals and to judge them accordingly on the basis of their own personal merits, rather than on the basis of the ethnic group that they belong to.

Yan Shen said...

Care to copy and paste a specific instance of my purported Asian supremacy? Or for that matter, care to copy and paste an instance where I racially denigrate another group?

Other Anonymous said...

"I think it's evil and borderline psychopathic to allow your readers to use explicit racial slurs against other ethnic groups."

I would not call Steve Hsu evil for allowing your racial slurs in this discussion.

"So for instance, you'll hear me call a spade a spade and refer to the white nationalist crowd as a group of mostly dim-witted rednecks, because from everything I've experienced, that characterization is remarkably accurate."

Civility education from someone who uses racially-charged language such as "dim-witted rednecks" would definitely leave something wanting.

ABCD said...

Yan Shen: Your Asian-supremacist utterances are frankly as much of a turn off as anything I see on Sailer's blog. With Hsu I get the sense that it's academic interest more than ethnic jingoism, but with you I get the sense that it's the other way around. My perception really - you're entitled to doing and saying what you please, but some admission of intent would be better than your holier-than-thou attitude.

Yan Shen said...

This is sadly all too true. Some people on white nationalist blogs feel like its perfectly acceptable to use explicit racial slurs against certain ethnic groups and even to advocate violence against them.

Yan Shen said...

Unfortunately, redneck isn't a racial slur like chink or gook. It refers to a specific segment of the white population, though it is of course used in a derogatory fashion.

http://en.wikipedia.org/wiki/Redneck

"Redneck is historically a derogatory slang term to refer to poor white Southern farmers in the United States.[1]"

It would be like me referring to a specific group of individuals as white trash. This would in no way be casting aspersions upon whites as a whole, because white trash is a term referring to a specific portion of the white population, mainly the white underclass. Just as there is white trash, there's also Asian trash, black trash, Hispanic trash, etc. A term like gook on the other hand, denigrates an entire ethnic group. This distinction is subtle, but of vital importance. This is why personal insults are permitted, i.e. referring to someone as a douchebag, but racial slurs are generally frowned upon.

You'll also note, that I'm using the term to describe a select group of unintelligent and bigoted people. I would never use the term without provocation against well-behaving whites. This is in stark contrast to the Steve Sailer crowd, who use explicit racial slurs against people who have done nothing more than engage in well reasoned discourse. I hope that this clarifies your confusion.
I hope that clarifies your confusion.

Yan Shen said...

I fail to see how a comment that contains nothing except an explicit racial slur is useful. You're right, not all of the comments on his blog are garbage. Some are decent. The ratio of garbage comments to insightful ones is remarkably high, however. A comment where I'm referred to as a gook, a chink, or slant eyed, probably contains nothing of value. You say that it's useful to know what others are really thinking. If an impartial reader were to read some of the more inflammatory comments on Sailer's blog, he or she would get the impression that the core constituency of his readership were Klansmen and Neo-Nazis. If an impartial reader peruses a sampling of the typical comments on Sailer's blog, he or she would get the impression that the average Sailerite was dim-witted and of mediocre intelligence. I've noticed this to be the case on many white nationalist blogs, where the majority of the comments are pitiful in quality. I think this is also what makes Sailer defensive when it comes to censoring his blog. Doing so would be a tacit admission that the white nationalist crowd is primarily composed of the riffraff, a fact which Sailer's psychological defensive mechanisms have taken great pains to bury.

Take for instance Dennis Mangan's blog. He censors comments which contain explicit racial slurs or which advocate violence against certain ethnic groups. In effect, he's telling his readers that reasoned discourse is perfectly fine, even on controversial issues such as race and IQ or white ethnic solidarity. Plain bigotry is unacceptable, inflammatory, and only helps to contribute to the decay of civilized discourse. I think everyone here knows that when you blog about HBD issues, you attract a variety of people, including hordes of the riffraff. If you want your blog to maintain any semblance of legitimacy, you should probably censor the comments on your blog. This is why for instance, the official Vdare.com blog doesn't allow for any kind of commenting at all. They know that because of the nature of the issues that they write about, if they permitted commenting, the Stormfront Neo-Nazi crowd would inundate the blog with garbage comments. And they want to distance themselves from that kind of association.

Of course, I've already stated why Steve Sailer won't censor his blog. His blog is his primary source of livelihood, and he knows all too well the mindset of his typical reader. So he has to pander to them and let them vent. I agree with Steve Hsu, in the sense that reasoned debate on any issue whatsoever should be permitted as long as the discourse is grounded within the facts and devoid of clear racial animus or malice. What I fail to see the value of, is in permitting comments that contain nothing except racial slurs and out-group hostility. That kind of garbage contributes nothing of importance to the discourse and probably only hampers it.

And let me reiterate one last fact. Sailer is half Jewish. That's why I get such a kick out of seeing him do his best Bobby Fischer impression on a daily basis.

steve hsu said...

Yes, most people have trouble distinguishing between statistical predictions (that only hold on average), and predictions about individuals, which are much noisier. The whole problem with racism, group differences, etc., could be resolved if people were just a little bit smarter about statistics and conditional probability.

Regarding Yan Shen's criticisms of your site, I have to say that while I disagree with many of the comments, some are very insightful. I think it's useful to read what other people are really thinking, and filters only make that more difficult. In making his site more polite by censoring comments, Steve runs the risk of making it sterile like mainstream media.

Anonymous said...

Not everyone shares your view of what is "acceptable discourse."

Anonymous said...

So then you, as a Chinese person (I'm guessing), are not allowed to criticize things that other Chinese people do?

Anonymous said...

Are you not also a big boy? Or is seeing "slant-eyed" going to ruin your life and keep your kids from going to college? I'm okay with impoliteness. And what's "derogatory"? People of Chinese descent do very frequently have different shaped eyelids than those of European descent. I don't personally have a problem with the different eyelid shape, but does everyone have to pretend they like your eyelids?

Catperson said...

"Note that once you fix the ability level (=SAT score) the remaining variance in GPA has about the same SD regardless of value of SAT score (vertical red lines in the big figure in the slides). That suggests that we can think of IQ and W as largely uncorrelated random variables"

No, it suggests that the relationship between IQ and GPA is linear. It tells you nothing about the relationship between IQ and W. Studies suggest that IQ and achievement motivation are indeed positively correlated. Working hard is often a smart decision.

Catperson said...

I think most people overestimate the role of pure blind luck. Good luck and bad luck tend to cancel out over the course of a person's life, so its effect on success is limited.

Joe said...

looking at this purely mathematically, I'm not quite sure why you ended up with with IQ + W. Shouldn't a generic Taylor expansion of a two variable function look more like c0 * IQ + c1 * W + c2 * IQ * W + c3 * IQ^2 + c4 * W^2 + ... ?

It's that third term that seems really interesting to me: the interplay of IQ and W. Throwing that away leaves a bad taste in my mouth. It seems unnatural to me that if W = 0 (sign up for a course and never show up to class), the grade is expected to be decent for a high IQ individual. Can anyone pass a chemistry exam without ever opening a chemistry book?

A generic Taylor expansion with so few terms usually implies smoothness and continuity. I think this function may indeed have interesting discontinuities (working just a little harder would get you to the next "level", etc). I'd venture a guess that Millennium prize category problems have effective discontinuities easily 4 SD above average for both IQ and W.

The constants also play a role. I imagine different problem domains had very different values for them. For example, if IQ tests are really testing IQ, they should be constructed such that c0 >> c1.

This is my first visit to your blog and I feel the contents of this comment are quite different from the other comments. Hope that's ok and I'm not totally off topic.

Nick said...

From my experience a major cause of underachievement is negative peer influence. The W factor captures personality x social environment interactions besides personality traits.

Yan Shen said...

One last thing. The entire world knows that your biological father was Jewish. Please try not to do your best Bobby Fischer imitation on a daily basis.

Yan Shen said...

Of course, admitting to a lapse in judgment would be too man of a thing for someone like you. Most likely you'll probably just ignore all of my perfectly valid points and go back to being the leader of the rednecks of America, all the while believing that your blog has some enormous degree of prestige and is read by the most intelligent and influential people in America. I used to wonder why you would let yourself be embarrassed by the pitiful quality of many of the comments on your blog. But then your persistent panhandling drives made me realize the obvious answer. Your blog is one of your primary sources of livelihood and you know all too well the mindset of the kinds of people who frequent your blogs. So you could care less whether or not most of your readers come off as being dim-witted degenerate rednecks. As long as they put money into your coffers, you're more than happy to pander to the riffraff of society. I suppose that's your choice. Who am I to tell you how you should or shouldn't make a living? Just be aware of the fact that consciously letting comments through your moderation which racially denigrate certain ethnic groups goes above and beyond the pale of acceptable discourse and verges on psychopathic behavior.

Yan Shen said...

Steve Sailer, in the future, please censor comments on your blog from people who refer to Chinese Americans as slant eyed. It's generally considered to be in very poor taste and racially derogatory. Since you're a self avowed citizenist, and Chinese Americans are also American citizens in many cases, I expect you to live up to your word. You're a big boy, and you should know better than to let those kinds of comments through your moderation. They go beyond the pale of normal and acceptable discourse.

Steve Sailer said...

The thing that throws people about IQ is that it works better at predicting group performance than individual performance. The odds that an individual physics major at the U. of Massachusetts will outperform over his career an individual physics major at MIT aren't good, but they aren't terrible, either. But the odds that the average physics major at UM will outperform the average physics major at MIT are non-existent.

That's not a particularly profound insight, but IQ touches on so many ego and political hot-buttons that you get people saying things like, "How can you generalize?" when it's much easier to generalize in predicting than to make predictions about specific individuals.

Yan Shen said...

Interestingly enough, that's also what poker pros say about luck, that over the course of a long career, everyone will be dealt both good and bad hands and so the effects of luck will tend to be mitigated somewhat.

Gal said...

Are you an idiot? Hsu is talking about the fact that the SD in GPA at fixed IQ is the same. So in his model GPA = IQ + W the data is fit by taking IQ and W to be uncorrelated Gaussian random variables.

Gal said...

So the Google founders will get leprosy at some point in order that things even out? I think you guys are confused about power law vs normally distributed randomness. Go read the Black Swan or a book on statistical distributions.

Yan Shen said...

Well you seem to be rather hostile for no reason at all. I never suggested anything of the sort. I just found Catperson's quote to be interestingly similar to what poker pros like to say about the role of luck in their game, which I suppose is much more normally distributed in nature. I've already read the book the Black Swan and would never doubt that many phenomenon in the real world are much better approximated by a power law distribution.

You could use a lesson though on how not to act like a douchebag.

Yan Shen said...

In fact Gal, let me conjecture a hypothesis about how the level of douchebag-ness is distributed throughout society. It's almost certainly not expected to be normally distributed. I call it the 99.99-1 rule. 99.99% of all of the aggregate douchebag-ness in all of human civilization is concentrated in just 1 person, you.

Catperson said...

Poker like a lot of other games, is an excellent metaphor for life. There's blind luck in chess too in that sometime you end up in an advantageous position you didn't plan or intend, but over the course of even a single game, let alone a whole series of games, good luck and bad luck cancel out and the more talented player wins. Luck means nothing unless you're smart or skilled enough to know what to do with it. Look at all the lottery winners who end up poor and miserable, despite achieving the purest form of luck imaginable. Luck is the residue of design.

Catperson said...

Look at Bill Gates. There was luck involved in briefly becoming the first centi-billionaire in history, but then bad luck when he was sued by the government causing his net worth to decline by billions, so good luck and bad luck canceled each other out to some degree, and the success he achieved on balance was largely a product of his incredible intellect and achievement motivation. Similarly for Martha Stewart. She was lucky and smart to time to her IPO in such a way that she briefly became a billionaire, but was unlucky and dumb to get embroiled in an insider trader scandal right when the government was on a corporate witch hunt causing her net worth to decline precipitously. So the good luck and bad luck canceled out, leaving her as a wealthy centi-millionaire and not the billionaire she aspired to be; a level of success commensurate with her intelligence, good looks and achievement motivation, but nothing beyond what she deserved. Look at Jon Gotti with his IQ of 110. With only a mildly above average IQ, he was luck that his crime payed off and he became a millionaire mob boss, but eventually bad luck canceled it out and he spent the rest of his life in jail.

Catperson said...

Among children, weight is influenced by both height and age, but children at fixed height have the same weight SD, so does that prove height and age are uncorrelated variables among children?

Yan Shen said...

http://isteve.blogspot.com/2010/09/national-merit-semifinalists-by-school.html

Well Steve Sailer and his readers are at it again. Basically the superior East Asian representation amongst national merit semifinalists is due to the result of East Asians "grinding it out". Sailer doesn't explicitly state as such, but you can infer that this is his general thesis, from the way that he words many of his posts. His claim is essentially that East Asian academic over-performance relative to whites can't be explained merely by a higher IQ alone, but mus reflect to a significant extent a vastly higher degree of conscientiousness as well.

Let me guess Sailer. When whites outperform blacks and Hispanics, it's due mostly to superior innate intelligent. When East Asians and Jews outperform whites, its always significantly due to work ethic, ethnic nepotism, etc.

Gal said...

"but children at fixed height have the same weight SD"

My suspicions about your intellect are confirmed. Compare the 10th and 90th percentile difference in weights of 4 foot tall children (of all ages) and the same for 6 foot tall children. They are very different.

It appears you don't know what "at fixed height" means, which is probably why you don't understand why it is nontrivial to have the same SD at any fixed GPA in the Hsu model.

Gal said...

Typo correction: last sentence should end: "to have the same SD in GPA at fixed SAT score in the Hsu model."

Catperson said...

Obviously your intellect is below average because you can't even type a sentence without making a typo. Also showing low intellect is the example you cite: "Compare the 10th and 90th percentile difference in weights of 4 foot tall children (of all ages) and the same for 6 foot tall children." Any intelligent person would realize that comparing weights across such a wide span of height would be problematic because among four foot tall children, you'd get a "floor effect" (look it up because you lack the brains to know what it is off the cuff) and six foot tall children are likely to have growth disorders causing their physical development to be irregular.

Anonymous said...

Maybe the reason you are so sensitive to these ideas is that you fear they are correct. Certainly history would support your fear, although the jury is still out. The truth can be very painful.

Gal said...

You still miss the point. Take 4 foot and 4 foot 6 if you like. The point is that you won't find the same weight SD for fixed heights but varying ages. Weight is not well modelled by a sum of two independent random variables height and age.

In the U Oregon data that Hsu analyzes the SD in GPA at fixed SAT (this measures the variance in W) is roughly constant. This implies that W is an *independent* random variable. After SAT is controlled for the remaining variation in GPA has constant mean and SD, and is normally distributed. This is why, even in popular folk language, smart/dumb and lazy/hard-working are considered independent descriptors.

Yan Shen said...

Actually, I find it highly implausible that Sailer's claim is in fact correct. I'm mostly amused that someone would deny something that seems to me to be fairly obvious. I'm also amused by the blatant double standard at play. I like your comment about the truth being very painful, because in many respects that sentiment would apply very well to the white nationalist community. Certainly, all of the elaborate hand-waving that white nationalists engage in when it comes to discussing East Asian and Jewish academic achievement makes it all to obvious that for some people, the truth can be a very bitter pill to swallow indeed.

Anonymous said...

Hehe, I didn't know this rage at the state of things was sizzling underneath the surface of the Asian community. That you have some emotional difficulties is the only way I can figure out what's wrong here. Are there a lot of people like you? It's strange, since I don't feel this rivalry at all.

Catperson said...

History would support that East Asians are superior. The printing press, money, weights and measures, the compass, gun powder-all invented in China. For centuries China was the richest and most powerful nation on Earth and could have easily discovered Europe and conquered the world if afflicted with the same primitive aggression that characterizes less evolved races. East Asian academic performance might be inflated to some degree by a good work ethic, however the primary cause is genetically more efficient information processing as evidenced by rapid East Asian complex reaction times and large East Asian brain size.

Catperson said...

I'm not missing the point, I just don't agree with it. Weight is influenced by height and age and height and age are correlated, so by your logic, when age is fixed and height varies, the weight SD for different ages should vary. And yet after the age where puberty starts, the weight SD for Iranian boys is about 11 kg at every age:

http://imsear.hellis.org/bitstream/123456789/576/2/jhpn2003v21n4p341.pdf

I'm no mathematician, but I've never heard any rule where if A and B both influence C, then the SD of C when you hold A constant reveals whether A and B are correlated. You just want to believe that hard work has nothing to do with intelligence because you're an unaccomplished lazy failure.

Yan Shen said...

I'm not sure why you would insist that there is rage or that I feel like there is a rivalry of any kind. As I've stated, I'm mostly amused.

Unlike the white nationalist community, who are a group of psychopaths who consistently believe that there is a cosmic race war going on, most normal people don't view the world through the same conceptual apparatus.

I'm also not sure why you would insist that I have emotional difficulties. My only guess would be that you have something that I would term a stupidity difficulty.

Gal said...

The "rule" you are looking for should involve two normally distributed variables like IQ and Conscientiousness (or Work ethic, as they call it). If there is a (strong) positive IQ and C correlation then GPA would have to depend nonlinearly on C in order to reproduce the results shown in Hsu's graph. (Not even sure this would work since it would distort other parts of the fit.) Of course there could be a small correlation but that would still mean the linear model (sum of two independent normally distributed variables) they use is a good approximation. Face it -- there are plenty of smart slackers and plenty of hard working thick people.

Catperson said...

Yes I agree there are plenty of hard working fools and lazy geniuses but overall I would expect at least a small correlation between hard work and IQ because working hard is often the smart decision and demonstrates future time orientation. As for this statistical rule you cite; my understanding is that usually when there is a linear relationship between A and B, the SD of B for people at a given level of A will be the same regardless of which level of A we're talking about, but I've never taken this to mean that all other variables that influence B are uncorrelated with A. That sounds impossible as a general rule.

Gooddaytoyouboy said...

Well, I think you are missing a variable.

Not only fluid intelligence and work matters, but the ability to memorize information. Say, a student with the same sat score, studying the same amount of hours as another student scores higher. this student probably has a better ability to memorize information.

You could test that, by asking the students to log how many hours they spend studying. Then, you can correct for sat scores and hours studying, and see which students have a better ability memorize info.

Gytryrt said...

Well, to seem really really smart, you have to memorize tons of info to do well in class, which may or may not be related to fluid intelligence a great deal.

Richard Seiter said...

Revisiting this old post in the context of discussion in http://infoproc.blogspot.com/2014/09/excellent-sheep-and-chinese-americans.html

Do you still feel that the underlying SAT and W variables are likely to be uncorrelated (in the general population) given the effects of truncated distributions noted in http://infoproc.blogspot.com/2014/07/success-ability-and-all-that.html ?

I think this discussion becomes especially interesting when you add creativity as discussed in http://medicalhypotheses.blogspot.com/2009/02/why-are-modern-scientists-so-dull.html

and potentially inverse correlations appear.

Alex Clark said...

Great post. I was checking continuously this blog and I am impressed!Very useful information particularly the last part :) I care for such info a lot. I was seeking this certain information for a long time.
Psychometrics Tests

Blog Archive

Labels