CHANCE News 2.08 
             (13 April to 24 April 1993)

Prepared by Laurie Snell

 Please send suggestions for  articles or format to 

Back issues of this chance news and other materials for a 
Chance course are on the Chance gopher.  Just point  your 
gopher to chance.dartmouth.edu  	


"Data! data! data!" he cried impatiently.  "I can't make 
bricks without clay."
                                  Sherlock Holmes




>>>>>==========>> 'Evil twin' helps even the odds in office betting pools. LA Times, 17 April, 1993, A23 Mark Stein A report of an article in the current Mathematical Monthly which your reporter co-authored with Peter Doyle and Joe DeStefano. The Dartmouth math department has a football pool in which each person puts in a dollar and tries to predict the outcome of, typically, ten football games with point spreads provided. Those with the largest number of correct choices divide the pot equally. Joe noticed that, because of the point spread, we were essentially tossing coins to make our choices. He further noticed that, by paying two dollars and putting in two entries one the mirror image of the other (the evil twin strategy), he could do better than the rest of us. Curiously, his advantage is independent of the number of games when the number of games is odd. <<<========<<

>>>>>==========>> Sex survey of American men finds 1% are gay. The New York Times, 15 April, 1993, A1 Felicity Barringer A study released by the Alan Guttmacher Institute estimated that the number of men who have engaged in homosexual sex is about 2 percent and who consider themselves exclusively homosexual is about 1 percent. These estimates are in contrast to the conventional ten percent said to have originated with the Kinsey studies. They are consistent with other large studies done recently at the University of Chicago and in Europe. The study was carried out by researchers at the Battelle Human Affairs Research Center in Seattle. It was based upon face to face interviews in which subjects were guaranteed anonymity. It contained lots of other information about the sex habits of American men. For example the median number of sexual partners was 7.3 for white men. No-one seemed to be bothered by a median of 7.3 for integer valued data but some papers like the NYT decided to call it a mean instead. (It was a median in the study). The study itself is reported in the March/April 1993 issue of Family Planning Perspectives. <<<========<<

>>>>>==========>> There were a lot of follow up articles on the Battelle sex study with interesting discussions of the difficulty of getting reliable answers in studies of this kind. See, for example, April 26 issue of Newsweek or the following NYTimes article. <<<========<<

>>>>>==========>> 'Measuring sexuality through polls can be shaky. The New York Times, 25 April, 1993 Felicity Barringer This article discribes a Harris poll that estimated that 4.4 percent of American men and 3.6 percent of women had sex with a same-sex partner in the five years before being interviewed. These results were part of previously unpublished research from a 1988 study of 739 men and 409 women aged 16 to 60. Taylor, president of Harris, comments on the difficulty of obtaining reliable figures and mentions some classic surveys to show the significance of measurement errors as compared to sampling errors. For example, a survey taken five years after Collier's magazine had ceased publication showing that a large number of people were still reading it. William Aquilino at Wisconsin has experimented with how answers differ depending on how the survey is done. For example, on an anonymous questionnaire 28 percent of the whites said that they had ever used cocaine as compared with 25% with the same question in a one-to- one interview, and 21% when asked over the phone. For blacks the corresponding figures were 23, 16, and 12. These percentages when asked about crack were 8 for confidential, 3 for interview, and 1 for phone. <<<========<<

>>>>>==========>> Why can't science get it right? LA Times 24 April, 1993, A1 Mark A. Stein The writer tackles the question: what do all the conflicting studies mean to the readers of newspapers? He discusses this in terms of examples, such as the recent studies about electromagnetic fields and cancer. He points out that the studies differ both in what they are measuring and the care with which they are carried out. He discusses topics such as bias, the difference beween markers and causes, "one swallow doth not a summer make" etc. A long well written article. <<<========<<

>>>>>==========>> Run vs. swim? statistician says the score is in. The New York Times, 21 April, 1993, C12 Gina Kolata An account of the article by Howard Wainer in the current CHANCE magazine (Vol. 6, No. 1). Wainer compared world record times in running and swimming and found that male championship runners go about 3.75 times further than swimmers in the same amount of time and female championship runners about 3.5 times further. In this time the swimmers burn 25 percent more calories. Thus running is more effecient and if you want to know if you are a more efficient runner or swimmer just compare your times for the same distance and see how your ratio compares with that of the champions. <<<========<<

>>>>>==========>> U. S. judge upholds population count. The New York Times, 14 April, 1993, A14 Felicity Barringer Judge Joseph McLaughlin of Federal District Court in Brooklyn ruled that Commerce Secretary Robert Mosbacher had not acted arbitrarily or capriciously in 1991 when he refused to adjust the 1990 census. (This case had famous statisticians testifying on both sides and their arguments were presented in Chance magazine V5 no. 3-4). The judge did say that those arguing for adjustment (Tukey, Feinberg, and others) had made a powerful case and that he would probably have ordered the adjustment if the court had been called on to decide the issue as the original arbiter in the case. <<<========<<

>>>>>==========>> China's crackdown on births: a stunning, and harsh success. The New York Times 25 April, 1993 Nicholas D. Kristof China's strict enforcement of their policy to restrict families to one or two children has made a dramatic drop in fertility rate from 2.5 in 1988 to 1.9 in 1992. The problem of the missing girls is mentioned. Normally there should be about 106 boys born for every 100 girls. In 1989 in China there were 113.8 boys for every 100 girls. This is explained in terms of under reporting, use of ultrasound for selective abortion etc. <<<========<<

>>>>>==========>> The economics of life and death. Scientific American May 1993 Amarty Sen Sen is a well-known Harvard economist who has long been interested in problems like the missing women and other population questions. In this article he argues that economists should supplement their standard financial indicators for countries by mortality data to get a better idea about questions like famine and hunger that bear on human well being. <<<========<<

>>>>>==========>> HIV and the etiology of AIDS. Lancet, 10 April, 1993 Letters Peter Duesberg Recent chance news reported two studies in Lancet meant to accept Duesberg's challenge to show that his theory that drugs are the cause of AIDS cannot be correct. Here Duesberg argues that, far from contradicting his theory, these studies confirm his drugs-AIDS hypothesis. <<<========<<

>>>>>==========>> Rethinking AIDS. Robert S. Root-Bernstein, Free Press Book review by David Perlman Root-Bernstein is another scientist who has challenged the theory that HIV is the cause of AIDS. claiming that "HIV is no more than a frequent, opportunistic infection associated with, but not necessary, to cause AIDS." The book is an appeal to look elsewhere for the complex causes of AIDS. <<<========<<

>>>>>==========>> Study ties DDT to cancer cases. The New York Times 22 April, 1993, A16 Associated press A report of a study in the current issue of "The Journal of the National Cancer Institute" which shows that women with the highest exposure to the pesticide DDT had four times the risk for breast cancer than women with the least exposure. This is suggested as a possible explanation for the rise in the incidence of breast cancer in recent decades in the U. S. Others have claimed that the actual rate has not increased but appears to have increased because improved testing methods have led to earlier detection. Even though DDT has been banned, it stays in the body for decades. <<<========<<

>>>>>==========>> Genetic counseling for families with inherited susceptibility to breast and ovarian cancer. Journal of American Medical Association, 21 April, 1993 Biesecker and others. Scientists believe that they are very close to identifying a gene (BRCA1) on chromosome 17 for which mutations predispose women to breast and ovarian cancer. It is estimated that about 1 in 200 women may be carriers of BRCA1 and, if they are, they have an 85% lifetime risk of developing breast cancer and an unknown additional risk for ovarian cancer. Even without this identification it is now possible to study family histories and using flanking markers to identify family members who have a high probability of having the BRCA1 gene. This article relates how a specific family was told that certain members had the high probability and others did not. It also explains roughly how they calculate things like the probability that a person in the family has the BRCA1 gene and then the probability that if she has it she will get breast cancer. It would be interesting to really understand how this is done. Other articles in the same issue provide a more technical analysis of linkage studies and the many problems that will have to be dealt with once the gene is identified--should there be widespread screening for the BRCA1 gene, effects on insurance policies etc. <<<========<<

>>>>>==========>> Is DNA testing foolproof? Mchael Ryan Parade Magazine 25 April, 1993 Another popular article on this popular question. Nothing much new in it. <<<========<<

>>>>>==========>> Molestation charges dropped after negative DNA tests. LA Times, 23 April, 1993, B4 Eric Young A case where DNA not matching got a suspect off. Until the results of the DNA testing came in, DNA the prosecutors felt they had a strong evidence against the suspect. The alleged victim picked the suspect from photos, witnesses said the accused was seen in area of the assault etc. <<<========<<

>>>>>==========>> Murder case puts DNA tests on trial; suspect's arrest was based on matches. Star Tribune, 14 April, 1993, 1B Randy Furst This is an account of the beginning of a trial that has been billed as a "historic battle over the validity of DNA testing". Attorneys on both sides say that Perez is the first person in the U.S. to be apprehended bases on DNA tests and put on trial. He is accused of sexually assaulting and strangling Jean Broderick in her Minneapolis apartment in November 1991. Before a match in DNA Perez was not a suspect. State law requires that sex offenders submit a sample and sample for DNA was taken when Perez left prison after serving time for a 1985 rape conviction. The judge, Peter Lindberg, ruled in a February pre-trial hearing that attorneys could not present statistical evidence on the accuracy of DNA testing. While other Minnesota judges have refused to allow prosecutors to allow population frequency statistics, legislators say they will attempt to mandate the admissibility of such statistical evidence in an amendment to a proposed omnibus crime bill under consideration. <<<========<<

>>>>>==========>> !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! CHANCE News 2.08 (13 April to 24 April 1993) !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! Please send suggestions to: jlsnell@dartmouth.edu >>>==========>>|<<==========<<<