Re: Race, intelligence, and anti-racist prejudice (Was: Genetic Evolution)
Frank Fujita (ffujita@sun1.iusb.indiana.edu)
Sun, 5 Feb 1995 05:25:08 GMT
JAMES BENTHALL (st26h@rosie.uh.edu) wrote:
: >>>Frank Fujita (ffujita@sun1.sun1.iusb.indiana.edu) wrote:
: >>>: JAMES BENTHALL (st26h@elroy.uh.edu) wrote:
: >>>: : All I.Q. tests fail the t-test. Variation within a population is always
: >>>: : greater than between populations.
: >>>: I'm unfamiliar with your usage of "t-test." Could you elaborate?
: If the variation between groups is much less than
: the variation within groups what enables us to say that they are *two
: differentiated groups*?
The extremely low probability that the two samples could have been drawn
from the same underlying population allows us to say that there are two
groups when we have a significant t-test EVEN WHEN THE VARIATION WITHIN
THE POPULATION IS GREATER THAN THE VARIATION BETWEEN POPULATIONS.
: I said t-test but what the professor actually said was the "analysis of
: variance" tests (ANOVA), but t-tests also analyze variance.
Indeed, the t-test is merely a special case of the one-way ANOVA where the
number of groups to be tested is two.
: Differences
: _between_ means are usually swamped by the variation _within_ populations.
: (Hopefully,everyone can understand this statement.)
No, I'm afraid that your use of the word "swamped" is ambigious. If you
mean that it is impossible to determine whether the two different observed
means come from the same underlying population then you are most certainly
wrong. If you mean that it is impossible to predict precisely which test
score belongs to a member of which group, then you would be right. However,
in either case, you statement is too vague to have a truth value.
: Standardized intelligent qoutient tests are usually felled by the analysis
: of variance.
This sentence is also too vague to be assigned a truth value, what do you
mean by "felled"? Is the test a tree that is turned into lumber by a
lumberjack (the ANOVA)?
: Differences between populations are so much greater than
: differences within populations that it makes it rather difficult to say
: generalizations such as "Population A tests consistently above that of
: population B." As a result, folks engaged in these kind of tests don't
: run ANOVA tests.
If I were to read you sentences litterally they would be meaningless. So,
I am going to assume that you tripped up here, and typed in the sentence
backward. Thus, I am assuming that your intention was to say that
"Difference within populations are so much greater than differences
between populations that ....."
That sentence would be meaninful, but false. Even when differences
within a population are much larger than differences between populations,
the t-test (and ANOVA) can make confident predictions about different
populations (consistently).
: I have no references, only the reassurance of an esteemed professor of
: anthropology that taught my stats class. If you want the truth you must
: INVESTIGATE. I, frankly, don't have time.
I can provide references, and though I am not an esteemed professor
of anthroplology, I do teach stats classes. Thus, I would suggest that
you print out this message, and be sure that your professor really
taught what you learned. If you receive her/his assurance that you
are right, please have him/her contact me.
Frank Fujita
|