W. Allen Wallis

Use of Ranks in One-Criterion Variance Analysis

Abstract Given C samples, with n i observations in the ith sample, a test of the hypothesis that the samples are from the same population may be made by ranking the observations from from 1 to Σn i (giving each observation in a group of ties the mean of the ranks tied for), finding the C sums of ranks, and computing a statistic H. Under the stated hypothesis, H is distributed approximately as χ2(C – 1), unless the samples are too small, in which case special approximations or exact tables are provided. One of the most important applications of the test is in detecting differences among the population means.* * Based in part on research supported by the Office of Naval Research at the Statistical Research Center, University of Chicago.

The Statistical Research Group, 1942–1945

Abstract The organization, work, membership, and influence of the Statistical Research Group, an Office of Scientific Research and Development activity at Columbia University during the Second World War, is described. A detailed account is given of the origins of sequential analysis in 1943, and a brief account of the origins at Stanford University in 1942 of the intensive courses in statistical quality control that were sponsored during the Second World War by the Office of Production Research and Development.

Statistics of the Kinsey Report

Abstract * Alfred c. Kinsey, Wardell b. Pomeroy, and Clyde e. Martin, Sexual Behavior in the Human Male. W.B. Saunders Company, Philadelphia and London, 1948. Pp. xv +804.

The Cochran-Mosteller-Tukey Report on the Kinsey Study: A Symposium*

6.50. The book is commonly referred to simply as “the Kinsey report,” since Kinsey initiated the project in 1938 (p. 10), and did about four-sevenths of all the interviewing that had been done up to the date of publication (p. 11). Similarly, it is common to write “Kinsey” where “Kinsey, Pomeroy, and Martin” or “the authors” would be correct. These abbreviated forms of reference are used throughout this paper.

The President's Column

Abstract * A review article on Statistical Problems of the Kinsey Report, by William G. Cochran, Frederick Mosteller, and John W. Tukey, with the assistance of W. O. Jenkins. Washington, D. C.: The American Statistical Association, 1954. Pp. x, 338.

Errata: Use of Ranks in One-Criterion Variance Analysis

5.00.

Compounding Probabilities from Independent Significance Tests

IMPROVING THE LANDSCAPE FOR PREVENTION It has been my pleasure to serve as President of the American Society for Preventive Cardiology (ASPC) over the past 2 years. During my tenure, we have revitalized our Society and strengthened our relationship with our journal, Preventive Cardiology. In November 2009 we held a joint symposium with the National Lipid Association prior to the American Heart Association’s Annual Meeting in Orlando, Florida. This symposium on ‘‘Overcoming Challenges in Cardiovascular Disease (CVD) Prevention: A Focus on the Cardiometabolic Risk Continuum,’’ enabled our Society to contribute our own special expertise to the proceedings, while strengthening our relationship with a partner society. My section, on treatment of hypertension based on global risk, was directly targeted at a key element of prevention and an example of how we convey our insights to the broader medical community. On March 5, 2010, we again reached out to partner organizations by participating in the Joint Conference–50th Cardiovascular Disease Epidemiology and Prevention and Nutrition, Physical Activity and Metabolism 2010, in San Francisco, California. We conducted a session on what has become a tradition for the ASPC, a debate on prevention guidelines that illustrated the range of opinion and depth of approach embraced by our field. We will continue to team up and partner with organizations that share our goals and mission and strengthen our Society while we enhance our branch of medicine. Note that there is an application for membership in the ASPC included in this journal and we invite you to apply for membership. We are looking forward to an active year in 2010, as health care is on the national agenda and prevention is in the spotlight and central to improving care and reducing costs and burden. By now our lawmakers are familiar with the grim statistics: over a third of adult Americans will experience coronary heart disease in their lifetimes. Whether the condition is angina pectoris, myocardial infarction, or coronary disease death, predicting the onset and occurrence of these events is critical in our clinical decision making. Going forward, practitioners should be thoroughly familiar with traditional approaches, as the multivariable prediction model developed by the Framingham investigators has been extensively validated with cohort studies and captures a range of factors, including age, sex, cholesterol level, and smoking status. Increasingly, we are seeing practitioners test the limits of our science. Physicians and other health care professionals are examining alternative measures of coronary heart disease and surrogate markers that may help to predict clinical events and guide preventive care in cardiology. Our task is to add to the body of knowledge and help researchers and clinicians alike gain greater insight into the process and theory of risk estimation. By gauging additional variables in models that include traditional risk assessment criteria, the statistical significance of alternate approaches may be clarified as to their predictive value. While there is room for improvement, our current standards for coronary heart disease risk assessment are proven to be relatively accurate. The value of new factors for assessment should be judged also for their applicability; traditional approaches are by now well understood and familiar to both clinicians and patients, and recommendations for medical therapy and lifestyle modification are practical and low in cost. Thus, while caution is warranted, we can also be cautiously optimistic that new developments now emerging from studies in omega 3 fatty acids and high-density lipoprotein cholesterol therapeutics will change and improve the landscape for diagnosis and prevention.