William Schucany, SMU professor emeritus of statistical science
Professor William Schucany became known as “Mr. Statistics” during his 40-year career with SMU. By the time he retired in 2011, he was called the heart and soul of the department. And even as an emeritus faculty member, he enjoys coming back to the Hilltop for a good seminar presentation.
To honor Schucany, the Department of Statistical Science has created the Bill Schucany Scholar Lecture Series, which will bring elite statisticians from around the world to SMU. Bradley Efron, Max H. Stein Professor of Statistics and Biostatistics at Stanford University and innovator of bootstrap technology, will be the inaugural presenter in two events scheduled for Thursday and Friday, Feb. 27-28, 2014.
“When people thought of our department, they thought of Bill Schucany,” says longtime colleague Wayne Woodward, professor and chair of the Department of Statistical Science in Dedman College of Humanities and Sciences. “Bill loves seminars – I think our Friday seminars were his favorite time of the week. We wanted to honor him, and we chose this as the thing that would mean the most to him.”
Schucany’s former students provided much of the series’ funding, which has been supplemented with departmental funds. Students, alumni and faculty members are all invited to attend the event, which the department plans to make an annual meeting.
The series’ first speaker is widely regarded as one of the most influential statisticians of all time, Woodward says. A member of the National Academy of Sciences and the American Academy of Arts and Sciences, Efron received the National Medal of Science for his contributions to the discipline, notably his innovation of the bootstrap technique. The method uses relatively simple yet computationally intensive techniques to produce accurate statistical estimates from very small random samples. Bootstrapping and its related computational techniques have greatly expanded the scope of statistical analyses, especially in the current environment of massive databases and computing capabilities.
“Anyone who would rank the top five statisticians in the world would include Brad Efron,” Woodward says. “He is an elite scholar who graciously accepted our invitation, probably because he holds Bill in such esteem. His Thursday evening talk is intended for a general scientific audience, and we encourage anyone with an interest to attend either or both events.”
Schucany himself is internationally recognized for his contributions to the field of nonparametric statistical inference. As a Fellow of the American Statistical Association (ASA), he was chosen in 2004 as one of only four ASA members to received its Founder’s Award, the highest honor the association bestows for service to the profession. Among numerous other honors, Schucany has received the national Don Owen Research Award from the San Antonio Chapter of the ASA and the Paul Minton Award from the Southern Regional Council on Statistics. In addition, he was elected to membership in the International Statistical Institute. Schucany has also served as editor of The American Statistician and as associate editor of the Journal of the American Statistical Association, the Journal of Educational Statistics, and Communications in Statistics.
Efron will give two public lectures during his SMU visit:
“Learning from the Experience of Others” – 7 p.m. Thursday, Feb. 27, location TBA. Familiar statistical estimates such as batting averages, political polls and medical trial results are obtained by direct observation of cases of interest. Sometimes, though, we can learn from the experience of “others” – e.g., there may be information about one player’s batting average in the observed averages of other players. Efron will present several examples showing how this works in practice, indicating some of the surprising theoretical ideas involved. The talk is intended for a general scientific audience.
“Frequentist Accuracy of Bayesian Estimates” – 3 p.m. Friday, Feb. 28, location TBA. In the absence of prior information, popular Bayesian estimation techniques usually begin with some form of “uninformative” prior, intended to have minimal inferential influence. Bayes rule will still produce nice-looking estimates and credible intervals, but these lack the logical force attached to genuine priors, and require further justification. This talk concerns computational formulas that produce frequentist accuracy assessments for Bayesian estimates. Both encouraging and cautionary examples will be presented.
Antibiotics rather than surgery may be the better treatment for cases of appendicitis in which the appendix hasn’t burst, according to a new study.
The study’s authors say the findings suggest that nonperforating appendicitis, as the disease is called when the appendix hasn’t burst, may be unrelated to perforating appendicitis, in which the appendix has burst. Instead, the study found that nonperforating childhood appendicitis, which historically has been treated with emergency surgery, seems to be a disease similar to nonperforating adult diverticulitis, which is often treated with antibiotics.
The study, “Epidemiological similarities between appendicitis and diverticulitis suggesting a common underlying pathogenesis,” was reported in the Archives of Surgery.
Childhood appendicitis and adult diverticulitis share many similarities, including association with colon hygiene and a low intake of fiber in the diet. Those shared epidemiological features prompted researchers to examine whether the two might be similar, according to SMU economist Tom Fomby.
Lead author on the study was Edward H. Livingston, M.D., in the division of Gastrointestinal and Endocrine Surgery at University of Texas Southwestern Medical School, Dallas; with the Department of Surgery, Veterans Affairs Medical Center Dallas; and in the Department of Bioengineering, University of Texas at Arlington. Also co-authoring was Robert W. Haley, M.D., in the Department of Internal Medicine-Epidemiology, UT Southwestern Medical School, and a past recipient of the SMU Distinguished Alumni Award.
The study looked at 27 years of data from the National Hospital Discharge Survey, which is compiled annually by the Centers for Disease Control and Prevention. The analysis specifically compared national data and regional data for children with appendicitis and adults with diverticulitis who were admitted to U.S. hospitals between 1979 and 2006.
The authors’ analysis shows that although the annual incidence rates of adult nonperforating diverticulitis and child nonperforating appendicitis changed greatly during the past 25 years, their secular patterns – long-term trends – followed the same general patterns, overall as well as region by region, according to the authors.
Diverticulitis, which is more common among people older than 60, occurs when pouches that have developed in the lining of the gastrointestinal tract become inflamed and sometimes infected, according to NDDIC. It is often treated with antibiotics, the authors say.
“These findings seem incompatible with the long-held view that perforating appendicitis is merely the progression of nonperforating disease where surgical intervention was delayed too long,” write the authors. “If perforating appendicitis was simply a manifestation of nonperforating appendicitis not treated in a timely manner, the secular trends should have been statistically similar, which they were not.”
What triggers appendicitis, and why is it more common in certain years and in the summer? SMU researchers have published evidence that a flu-like virus is to blame.
Dedman College Professors Tom Fomby, Economics, and Wayne Woodward, Statistical Science, reviewed 36 years’ worth of hospital data on cases of appendicitis, influenza and gastric viral infections. They discovered that appendicitis admissions peaked in the years 1977, 1981, 1984, 1987, 1994 and 1998.
The clustering pattern suggests that appendicitis outbreaks are typical of viral infections. The data also showed a slight increase in the number of appendicitis cases during the summer months.
A new study of veterans of the 1991 Gulf War suggests that exposure to neurotoxins such as anti-nerve agent pills, insect repellent and Sarin caused neurological changes to their brains.
Researchers at the University of Texas Southwestern Medical Center, Southern Methodist University, and the Veterans Affairs Medical Center in Dallas performed digital brain scans on 21 chronically ill Gulf War veterans from the same Naval Reserve construction bairttalion, all of whom had symptoms of Gulf War syndrome.
Richard Gunst, Wayne Woodward and William Schucany, professors in SMU’s Statistical Science Department, are collaborating with imaging specialists at UT Southwestern Medical Center to compare brain scans of people suffering from the syndrome with those of a healthy control group. They are pioneering the use of spatial statistical modeling to analyze brain scan data from Gulf War veterans, aiming to pinpoint specific areas of the brain affected by Gulf War Syndrome.
The SMU team is working with UTSW epidemiologist and 2008 Dedman College Distinguished Graduate Robert Ware Haley. Haley, one of the foremost experts on the syndrome, earned B.A. degrees in philosophy and social sciences from SMU in 1967.
A congressionally mandated study has revealed that 1 of every 4 veterans of the 1991 Gulf War suffers from neurological symptoms collectively referred to as Gulf War syndrome. The Research Advisory Committee on Gulf War Veterans’ Illnesses began work in 2002 and presented its report to then-Secretary of Veterans Affairs James Peake in November 2008.
Statistical Science Chair Wayne Woodward was honored as the 2006-07 United Methodist Church University Scholar/Teacher of the Year at SMU’s fall General Faculty Meeting Aug. 29. President R. Gerald Turner updated the faculty on important developments in campus life and the status of the George W. Bush presidential library complex. More under the link.