From: Jake Shannon (jakeshannon@usa.net)
Date: Mon Feb 28 2000 - 10:33:01 MST
Type II Error in the Bell Curve
or
Racists, Damn Racists, and Charles Murray
by Jake Shannon
"A null hypothesis is always one of status quo or no difference... A Type II
error occurs if the null hypothesis Ho is not rejected when in fact it is
false and should be rejected."
(David Levine, 1998)
While thumbing through The Bell Curve, I found problems with surveying errors
in the book. It is essential to examine the purpose of the survey, why it was
conducted, and for whom. Technically speaking, there are four types of survey
error (Groves, R. M., Survey Errors and Survey Costs, New York: Wiley, 1989):
1. coverage error- results from the exclusion of certain groups of subjects
from this population listing so that they have no chance of being selected in
the sample.
2. nonresponse error- results from the failure to collect data on all subjects
in the sample.
3. sampling error- reflects the heterogeneity or "chance differences" from
sample to sample based on the probability of subjects being selected in the
particular samples.
4. measurement error- refers to inaccuracies in the recorded responses that
occur because of a weakness in question wording, an interviewer's effect on
the respondent, or the effort made by the respondent.
Murray and Hernnstein commit at least the first and fourth errors IMHO. The
fact that they get a normal distribution when they sample a large group of
subjects should be no surprise to anyone familiar with statistics. The problem
is GIGO (garbage in, garbage out). I met Murray once while he was speaking in
front of a decent sized libertarian audience at Laissez Faire Books where he
caught a lot of flack.
"This book is about differences in intellectual capacity among people and
groups and what those differences mean for America’s future", so begins The
Bell Curve. This benign looking sentence doesn't just have "issues", it has an
entire subscription.
This sentence is correct until the first coordinating conjunction. It is
obvious that intellectual capacity differs among individuals. Thomas Sowell’s
intellectual capacity is very different from say, Pauly Shore’s intellectual
capacity. What is not so obvious is the word sandwiched between "and"s in the
aforementioned quote. The word "groups" makes Murray and Herrnstein’s premise
guilty of the fallacy of composition. Is it true that if intellectual capacity
among individuals varies, then intellectual capacity among groups of
individuals must vary too? Of course not, it is not necessarily true that if
something is true of the parts, then it is also true of the whole. (Dustin
Hoffman and Warren Beatty are both good actors but did that make Ishtar a good
movie?) Ask yourself, "How are these groups determined? What is the
differentia in defining who belongs to which group?" Shoe size? Skin color?
Baldness?
Are the East Asians superior to Europeans cognitively? Murray and Herrnstein
say, "[t]he universality of the contrast in nonverbal and verbal skills
between East Asians and Europeans whites suggests, without quite proving,
genetic roots." What business do they have to make such a claim without proof?
None, it just shows that they have no qualms about parading arbitrary
categories in order to justify political ends.
Sure, individuals differ cognitively, but do groups? No, a race cannot think,
and if it cannot cognate how can it differ cognitively from other races?
Murray and Herrnstein go so far as to rank races anyway with the help of
psychometricians. According to them, ethnically the order from highest to
lowest is Ashkenazi Jews, East Asians, Europeans, and African Americans.
Female philosopher/novelist Ayn Rand said it best. "The question of whether
one alleges the superiority or the inferiority of any given race is
irrelevant; racism has only one psychological root: the racist’s sense of his
own inferiority."
With Liberty and Justice,
Jake Shannon
http://www.eternalvigilance.org
____________________________________________________________________
Get free email and a permanent address at http://www.netaddress.com/?N=1
This archive was generated by hypermail 2.1.5 : Fri Nov 01 2002 - 15:27:05 MST