[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

*To*: [email protected]*Subject*: Re: Public Schools*From*: Robert Hettinga <[email protected]>*Date*: Fri, 27 Sep 1996 09:10:44 -0400*Sender*: [email protected]

I forwarded this to someone, who said: --- begin forwarded text From: somebody Date: Fri, 27 Sep 1996 00:26:28 -0400 To: [email protected] Subject: Re: Public Schools Bob, I'm not sure I want to get my name on this particular set of info, but the story on IQ and SAT scores is, to a certain extent, spelled out in "The Bell Curve." The simple, short version is for IQ where the distribution is nearly normal with a mean of 100 and a standard deviation of 15. (Recall that, in a normal distribution, two standard deviations above the mean (2-sigma) is achieved by only 1-2%, and 3-sigma, by a factor of 10 fewer.) There used to be a simple (public) answer for the SAT: mean of 500 and standard deviation of 100. So 500 = 100 and 800 = 145? Well, maybe. The answer for SAT (verbal) scores (1961 data only, sorry) is neither short nor simple. The distribution is decidely non-normal. The peak is at 280-ish, and the high side looks kind of like a normal distribution. If it were, the standard deviation would be 170 or so. Because of this, the average is 475-ish. Oh, well. Thus, maybe, an SAT of 800 = an IQ of 145. But 475 = 100? Or is it 280 = 100? And of course, the populations aren't even close to the same. Only those who might go to college take the SAT. And in 1961 that was even more so. Maybe that's why they call them social scientists. --- end forwarded text Cheers, Bob Hettinga ----------------- Robert Hettinga ([email protected]) e$, 44 Farquhar Street, Boston, MA 02131 USA "'Bart Bucks' are not legal tender." -- Punishment, 100 times on a chalkboard, for Bart Simpson The e$ Home Page: http://www.vmeng.com/rah/

- Prev by Date:
**HBO_ped Phill's AP Op-Ed** - Next by Date:
**Re: Newsgroup proposal: misc.anonymous** - Prev by thread:
**Re: Public Schools** - Next by thread:
**Re: Public Schools** - Index(es):