A. Russell Localio, Ph.D.

Russell Localio, Associate Professor of Biostatistics, joined the biostatistics faculty at the University of Pennsylvania in 1997. He has worked for several decades on the methodological issues of research in adverse events in medicine, agreement on the causes of these events, and medical professional liability, and has been the PI of both an R01 and an R03 grant on this subject. He is currently co-director of the Pediatrics Biostatistics Section within the Division of Biostatistics in the Department of Biostatistics and Epidemiology. His current methodological work centers on model misspecification for estimating risk difference and relative risk estimates in complex designs such as occur in multi-center studies, cluster randomization designs, meta-analyses, confounding by cluster in longitudinal study designs, and the appropriate use of baseline outcomes in longitudinal studies. Ongoing collaborative work includes studies on the accuracy and reliability of multimodality radiological imaging for breast cancer, weight loss programs in primary care, randomized trials of electronic medical records alerts and reminders for the treatment of asthma, otitis media, the use of childhood vaccines, and a randomized trial of feedback to physicians of information on inappropriate antibiotic prescribing. Other randomized studies include interventions to improve referral for problems in childhood development, to improve the primary care of premature infants, and a multi-year intervention to reduce symptoms of post traumatic stress disorder. He is currently also collaborating on observational studies on the frequency of colonoscopy screening in older adults and on the variation in the use of psychotropic drugs among children, the relationships of health care utilization and foster care for children, and the causes and mediators of family violence among recently deployed members of the U.S. Armed Forces. For 8 years, Professor Localio was course director of the second semester required biostatistics class in the Masters of Science in Epidemiology Program, and he is currently course director in a two-semester course on longitudinal and clustered data analysis. He serves on several PhD dissertation committees, and is the formally named statistical advisor and mentor on many ongoing career development awards (K awards). Professor Localio served as a member of the National Committee on Vital and Health Statistics in the Department of Health and Human Services from 2003-2006, and has been an associate editor of Annals of Internal Medicine since 1997.

Selected Publications

  • Localio AR, Berlin JA, Ten Have TR, Kimmel SE. Adjustments for center in multicenter studies: An overview. Annals of Internal Medicine 135:112-123, 2001.
  • Localio AR, Berlin JA, Ten Have TR. Confounding due to cluster in multicenter studies – causes and cures. Health Services and Outcomes Research Methodology 3:195-210, 2002.
  • Gasink LB, Blumberg EA, Localio AR, Desai SS, Israni AK, Lautenbach E. Hepatitis C virus seropositivity in organ donors and survival in heart transplant recipients. Journal of the American Medical Association 296:1843-1850, 2006.
  • Localio A R, Berlin JA, Ten Have TR. Longitudinal and repeated cross-sectional cluster-randomization designs using mixed effects regression for binary outcomes: bias and coverage of frequentist and Bayesian methods. Statistics in Medicine 25:2720-2736, 2006.
  • Localio AR, Zhou L, Norman SA. Measuring screening intensity in case-control studies of the efficacy of mammography. American Journal of Epidemiology 164(3):272-281, 2006.