!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
CHANCE News 2.21
(12 December to 31 December 1993)
!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
Prepared by J. Laurie Snell as part of the
CHANCE Course Project supported by the
National Science Foundation and the
New England Consortium for Undergraduate
Science Education.
Please send suggestions to:
dart.chance@dartmouth.edu
Current and previous issues of CHANCE
News can be found on our chance gopher.
Just point your gopher to:
chance.dartmouth.edu
====================================
"Statistics are the triumph of the
quantitative method, and the quantitative
method is the victory of sterility and death"
Hilaire Belloc
====================================
ARTICLES ABSTRACTED
>>>>>==========>>
John Finn suggested the first item:
Taking your Chances: An Explanation of Risk
Assessment and the Psychology of Worry
Old Farmer's Almanac 1994, 220-222
Jon Vara
This is a very nice, brief article about risk. Vara
supplies details often left out when people give
odds for rare events. For example, when giving the risk
of being struck by a small meteorite, he mentions
that in 1954 a Mrs. Hodges became the only human
confirmed to have been struck by a falling
extraterrestrial body. (A dog was killed by a three
pound meteorite that fell on Egypt in 1911).
In an average year, half a dozen small meteorites
strike the Earth close enough to human observers to
be recovered, but one's annual risk of being hit by one
is estimated to be only one chance in 17 billion.
Chances for a globally catastrophic asteroid strike
are estimated to be much higher, one chance in
500,000 giving a respectable one chance in 7,000
over a 70 year lifetime.
A number of interesting tables are given. For
example, a table of risks estimated to increase the
probability of a person'sdeath in any year by one
chance in a million. From this you learn that traveling
by bicycle ten miles, by car 300 miles or by jet 1,000
miles all increase your chance of death by one in a
million.
<<<========<<
>>>>>==========>>
Frazier Will Remain No. 1 in Savvy.
The New York Times, 15 December 1993, B14
Harvey Araton
In discussing the fact that Frazier was about to lose
his record of 14,617 points as a Knick to Ewing,
Araton tells the following story:
When Frazier was in college, a Southern Illinois
Saluki, there was a practice-ending drill that
required the five starters to hit 10 free throws
consecutively, two apiece, before they could leave.
Frazier, the star, was not the highest percentage
shooter, nor was he able to focus like the others, who
were capable of making 25, even 50, straight.
Frazier said that despite this, he was always the last
shooter up, gunning for 9 and 10, his teammates' fate
in his hands.
"By the time they got around to 6 and 7, then 7 and
8, the pressure was starting to mount," he said. "By
the time they got to 9 and 10, everybody would be
standing there, looking at me, saying, 'You better not
miss.' "
Matthew Poage pointed out that if they really
wanted to get home sooner, they should have
let the better free throw shooters go last.
<<<========<<
>>>>>==========>>
Study Links Miscarriages to Caffeine Consumption.
The New York Times, 22 December 1993, A18
Tim Hilchey
A study in the most recent Journal of the American
Medical Association reports that drinking more than
the amount of caffeine in three cups of coffee a day
during pregnancy nearly triples the risk of a
miscarriage.
A study reported in the same journal in February
suggested that drinking three or fewer cups of coffee
a day did not increase the risk of miscarriage or
affect fetal development. These studies were
considered somewhat contradictory and an
accompanying editorial attempts to explain how this
might happen -- huge range in cup sizes, variability
in caffeine content of coffee brewed in different
places, etc.
<<<========<<
>>>>>==========>>
In Debate on Radiation Tests, Rush to Judgment is
Resisted.
The New York Times, 1 Jan 1994, 1-1
Gina Kolata
Energy Secretary Hazel O'Leary has asked that an
investigation be carried out on the studies done by
government agencies and others in the 50's and 60's
to determine the harmful effects of radiation. These
include studies in which terminally ill patients were
injected with lethal or near lethal doses of radiation
to see its effects, prisoners were irradiated to learn
what doses of X-rays made men sterile and mentally
retarded children received trace amounts of
radioactive minerals to study human metabolism.
Experts point out that it is necessary to judge these
experiments in the context of the time. Little was
known about the danger of radiation; modern ethical
standards and informed consent were not well
established, and so on. They point out that the
studies are not secret and in fact appear in current
literature and help to determine, for example,
the safe amount of radiation during chemotherapy.
There is a curious debate going on about whether the
data from these experiments should somehow be
tagged and not used in a routine way.
<<<========<<
>>>>>==========>>
W. Edwards Deeming, Expert on Business Management, Dies at 93.
The New York Times, 21 December 1993, B7
John Hellish
The Quality Gospel According to Deming: A Man
Revered for His Influence on Corporate
Competitiveness in the U.S. and Japan.
Financial Times, 30 December 1993, M8
Martin Dickson
W. Edwards Deming died on December 20 at the age
of 93. All major newspapers carried his obituary.
These are two of the more complete discussions of
his life. There was also an interesting interview with
Myron Tribus about Deming on the radio show on
National Public Radio? "All Things Considered" that
can also be found in the full text articles.
The New York Times article tells the familiar story
of Deming's initial successes with quality control,
first in Japan and then in the United States with Ford
and Xerox. It mentions his general theory of
management and his vigorous life, running
workshops right up to the time of his death.
The article in the Financial Times ties in Deming's
work with others including his collaboration with the
founder of quality control, Walter Shewhart, and Deming's
co-worker in Japan, Joseph Duran, himself on his
final tour at age 89.
<<<========<<
>>>>>==========>>
Is Industrial Statistics out of Control?
Statistical Science, 8(4), November 1993, 356-409
David Banks.
While the author does not limit himself to quality
control, this article and the comments on it are good
places to get a "non hype" view of the work of
Deming and others in bringing quality control to
industry.
Some of Banks' statements are controversial, for
example, his statement:
>> That statistical methodology is
>> responsible for the Japanese success
>> story is a myth fostered by the 1980
>> NBC television special on the Deming
>> story "If Japan Can, Why Can't We?"
Banks feels that the ideas behind Total Quality
Management (TQM) are useful, simple, and not
deep. He remarks that "TQM has worked very
successfully in diverse industries, and the nation's
economic engine would doubtless run more smoothly
if it were more widely employed." He goes on to say,
however: "There are dangers in TQM. As
implemented, it tends to be enshrined, and this
stifles creative solutions." This assessment of TQM
guarantees a lively response by the other well-
known statisticians who act as discussants for
Bank's article.
A more positive view of TQM and of Deming's work
is presented by Robert Hogg as one of the
discussants.
The article, and the discussion that follows it,
provide a down to earth and insightful analysis of
Total Quality Control , in particular, and industrial
statistics in general.
<<<========<<
>>>>>==========>>
Breast Cancer Screening Under 50: Experts Disagree
if Benefits Exist.
The New York Times, 14 December 1993, C1
Gina Kolata
Mammogram Debate Moving From Test's Merits to
Its Cost.
The New York Times, 27 December 1993, A1
Gina Kolata
Eight studies in the past 30 years have consistently
found that routine mammograms for women over 50
reduce the death rate from breast cancer by at least
25%, but have not found a significant reduction for
testing in younger women. Combined, the studies
include 173,000 women in their 40's. Considered as
a group, the studies do not show a statistically
significant advantage for those women who had
mammograms.
Based on these studies, the National Cancer Institute
has changed its recommendation that women under
50 have mammogram tests. It now recommends that
women under 50 be informed of the results of
present scientific studies and be encouraged to make
their own choice. Other agencies continue to
recommend mammograms for women under 50 and
this article provides expert opinions on both sides of
this issue.
Those who argue for testing remark that "it is better
to be safe than sorry" and that women who do not
have the test and later develop breast cancer will
blame themselves. They also suggest that the studies
are not all that convincing. They claim, for
example, that the patients were not followed for a
sufficiently long time and that mammogram
techniques have significantly improved since these
studies.
On the other side, you have the arguments that the
large number of false positives lead to unnecessary
fears, additional testing and even surgery and that
the expense for a small number of successes is huge.
The second article emphasizes the economic issues.
Using the number of women who had mammograms
in 1990, it is estimated that the cost is about half a
billion dollars. It is argued that, in thinking about a
national health plan, this is a lot of money to spend
on testing that has not been demonstrated to have
statistically significant effect.
Of course, some women under forty who develop
breast cancer could have had it prevented by such
tests. Thus, women argue that they should not be
treated as a "statistic", but rather as a human being,
and if they want to have a mammogram test, it
should be paid for.
This shapes up to be a mighty battle between those
who feel that, if the line is not held here, it will
never be held -- health care costs will continue to
spiral -- and a powerful movement among women to
do everything possible to decrease the very high
mortality rate of breast cancer.
<<<========<<
>>>>>==========>>
Study Yields Best Evidence that Alcohol Helps the
Heart.
The New York Times, 16 December 1993, B15
Associated Press
Men Should Quaff Five Bottles Of Wine a Week,
Study Says.
The Ottawa Citizen, 28 December 1993, A2
Peter Pallot
The Times article discusses a study published in the
current New England Journal of Medicine that
showed that moderate alcohol consumption cuts
heart attack risk in half. It is believed that this is
because such moderate drinkers have about 15
percent higher levels of high-density lipoprotein
(HDL) cholesterol than those who do not drink.
HDL is said to prevent heart disease by cleansing
the blood vessels of fatty buildups.
The study questioned 340 recent heart attack victims
about their drinking habits. They compared them
with healthy people about the same age and sex.
Consuming one to three drinks daily reduced the
risk, but more than three drinks a day did not lower
the risk further.
The second article reports on a speech given by Sir
Richard Doll. He spoke on his continued work with
his 1954 study of doctors that first demonstrated that
smoking caused lung cancer. Of the 40,000 male and
female doctors in the smoking study, 12,000 men
later recorded their drinking habits over a period of
years. It was found that the healthiest were non-
smokers consuming 20-29 units of alcohol weekly.
Units are in terms of whiskey and I assume they
mean a shot and 29 units corresponds to 4.8 bottles
of wine or 14.5 pints of beer.
Doll comments that U.S. studies have suggested a
level of consumption that is only about half what he
found to be optimal.
All researchers point out the obvious dangers of
drinking and do not suggest non-drinkers rush out
and start drinking.
<<<========<<
>>>>>==========>>
The Power of Faith.
Newsday, 21 December 1993, Discovery 61
Bob Keeler
Dr. Larry Dossey was intrigued by a study in 1988
that was a double blind randomized experiment with
393 cardiac-care patients showing that cardiac
patients prayed for by others did significantly better
than the control group. It was published in the
Southern Medical Journal (July 1988, 81(7)). Apparently,
such studies are normally published in parapsychology
journals.
Dossey then took time out from his medical practice
to review the literature on this subject and was
convinced that the evidence for the effectiveness of
prayer was overwhelming. (A colleague observed
that he certainly prayed for the outcome of all of his
experiments.) The results of Dossey's study can be
found in his new book "Healing Words," published
by Harper Collins.
Theories like this have obtained a new respectability
through the new HIH Office of Alternative Medicine
that has begun funding in this area among others.
We will probably be hearing more about this book
from the Skeptical Inquirer.
<<<========<<
>>>>>==========>>
U.S. Survey Estimates Infections with HIV Outside
Risk Groups.
The New York times, 14 December 1993, C10
Lawrence K. Altman
The usual estimate of one million people in the U.S.
infected with the HIV virus comes from computer
models and has come under attack as not being a
reliable estimate.
The first randomized survey to determine the
number of HIV positive people in the U.S. was
conducted with 7,782 individuals from 18 to 59
years old, randomly chosen from 44 communities
throughout the country. Twenty-nine people (22
men and 7 women) were found to be infected giving
an estimate of 0.39 percent. This would lead to an
estimate of 550,000 in the country.
This estimate is thought to be low because the
response from young men was poor and because
limits in the design of the survey excluded many
people at high risk for infection -- the homeless,
those living in hospitals, prisons and other
institutions. Those who conducted the survey
thought that the previous figure of one million was
probably pretty good.
<<<========<<
>>>>>==========>>
For Stock Market Advice, Just Call the
Meteorologist for Manhattan.
Wall Street Journal, 12 December 1993, B1
Steve Stecklow
Finance professor Edward M. Saunders at the
University of Massachusetts analyzed 63 years of
weather data in Manhattan and compared the data
with the daily Dow Jones Industrial Average. The
Dow was up 46% of the time on sunny days and
49.5% of the days when the weather was overcast or
raining. Overall, it was down 48.5% of the days.
Since 1982, the weather effect has been diminishing.
Saunders attributes the change to the increasing
globalization of market trading and the advent of
futures trading in Chicago. On the days of both the
1929 and 1987 stock market crashes the weather on
Wall Street was pleasant.
Saunders' study appears in the December issue of the
American Economic Review.
<<<========<<
>>>>>==========>>
Mudslinging on the Earth-Beat.
The Amicus Journal, Winter 1994, 39-44
Francesca Lymna
This is a report of a recent meeting of the Society of
Environmental Journalists. There was a session on
"backlash" and this article contains selections from
speeches at this session. The point is made that
environmental writers have often in the past become
captives of environmentalists and written their
articles in an advocacy manner without much critical
analysis of the problem.
Now, apparently, there is a danger the other way that
these writers will become captives of the anti-
environmentalists and become excessively skeptical
of environmental hazards.
The speakers all discuss the difficulties they have
understating the concept of uncertainly and the
extent to which they need to explain this concept to
their readers in the context of the environmental
issue they are reporting.
<<<========<<
>>>>>==========>>
Who's Really #1?: Choose Your Math and Get the
Rankings You Want.
Science News, December 18 & 25, 1993, 412-413
Ivars Peterson
Anyone who has followed football at all this year is
aware of the difficulty of deciding which college
football team is the best in the country. This article
describes some mathematical and statistical tools
that have been used in trying to rank sports teams in
general and football teams in particular. The most
recent is a method developed by James Keener
described in the March SIAM Review based
on some earlier work of Joe Keller. Keller was
trying to rank the SIAM journals using
such information as the number of times they were
cited by other publications. He wasn't very satisfied
with the results, so applied his ranking techniques to
baseball where he felt he had more success.
Harvard statistician Hal Stern has studied the way
that the New York Times and USA Today determine
team rankings. Evidently, they keep their method a
secret, but Stern feels that at least USA Today uses a
fairly standard least squares method. He stresses
that the method you should use depends upon
whether you are using the rankings to predict
outcomes of future games or to determine
participation in a championship playoff.
<<<========<<
>>>>>==========>>
Here are several
articles from our Boston reporter Bill Peterson.
Ask Marilyn.
Parade Magazine, 26 December 1993, 9
Marilyn vos Savant
>> Somehow you've overcome extreme odds
>> and flipped 100 consecutive 'heads.' The
>> chances of flipping another head on the next
>> toss can't possibly be as great as 50-50, can
>> they?
writes a reader. Marilyn gives something of a
Bayesian answer, saying that they're probably far
greater than that, unless we're absolutely sure the
coin is fair, in which case the chances would, indeed,
be 50-50.
<<<========<<
>>>>>==========>>
A Short-Range Solution: Bahr Steps in for Sisson.
The Boston Globe, 16 December 1993, 89
Ron Bourges
Can we handle another sports story? This one
describes the New England Patriots' addition of
veteran place kicker, Matt Bahr, to give their
inconsistent rookie Scott Sisson a break. The story
reports that although Bahr's career field goal
accuracy of 0.718 puts him ninth in league history,
"this season Bahr is connecting at only a 0.615 rate
(8 for 13), well below his career figure." It's easy to
check that this year's "sample" is not large enough
for the difference to be statistically significant under
a simple binomial model. Bahr, at least, seems to be
aware that these things aren't settled by hypothesis
tests anyway, quoting another famous place kicker
(Jan Stenerud) to the effect that you're always two
misses away from retirement.
<<<========<<
>>>>>==========>>
Here is an extended quotation which seems
appropriate for this month when Ed McMahon
will be hawking the Publishers' Clearinghouse
sweeps, and a number of even less reputable
contests are in season!
He was a few paces away from them when
suddenly the group broke up and two of the
men were in a violent altercation. For a
moment they seems almost on the point of
blows.
"Can't your bleeding well listen to what I say?
I tell you no number ending in seven ain't won
for over fourteen months!"
"Yes it 'as , then."
"No, it 'as not! Back 'ome I got the 'ole lot of
'em for over two years wrote down on a piece of
paper. I takes 'em down reg'lar as the clock.
An' I tell you, no number ending in seven--"
"Yes, a seven 'as won! I could pretty near tell
you the bleeding number. Four oh seven, it
ended in. It were February--second week in
February."
"February your grandmother! I got it all down
in black and white. An' I tell you no number--"
They were talking about the Lottery. Winston
looked back when he had bone thirty meters.
They were still arguing, with vivid, passionate
faces. The Lottery, with its weekly pay-out of
enormous prizes, was the one public event to
which the proles paid serious attention. It was
probable that there were some millions of
proles for whom the Lottery was the principal if
not the only reason for remaining alive. It was
their delight, their folly, their anodyne, their
intellectual stimulant. Where the Lottery was
concerned, even people who could barely read
and write seemed capable of intricate
calculations and staggering feats of memory.
There was a whole tribe of men who made a
living simply by selling systems, forecasts, and
lucky amulets. Winston had nothing to do with
the running of the Lottery, which was managed
by the Ministry of Plenty, but he was aware
(indeed everyone in the Party was aware) that
the prizes were largely imaginary."
--George Orwell, "1984"
<<<========<<
>>>>>==========>>
200% of nothing: an eye-opening tour through the
twists and turns of math abuse and innumeracy.
A.K. Dewdney
Wiley, New York 1993.
A. K. Dewdney, well known for his columns on
Mathematical Games and on computing in the Scientific
American, has written a book on numeracy. Through the
years, his readers, who he calls "abuse detectives"
have sent him interesting examples of the abuse of
mathematics from the press.
In this book, Dewdney presents many of these examples
together with his ideas on what an average person
should know about mathematics to avoid being misled by
advertisements and news reports on television and in
the newspapers. Not surprisingly, statistics and
probability plays an important role in this.
The title of the book came from an advertisement which
claimed that a new light-bulb would save 200 percent on
electricity costs. A reader wrote to the company
suggesting that he should be paid for using the light-
bulbs since, if the claim is correct, he would be
generating electricity.
<<<========<<
>>>>>==========>>
!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
CHANCE News
(12 December to 31 December 1993)
!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
Please send suggestions to: jlsnell@dartmouth.edu