Converting Data into Evidence (eBook)

Converting Data into Evidence: A Statistics Primer for the Medical Practitioner provides a thorough introduction to the key statistical techniques that medical practitioners encounter throughout their professional careers. These techniques play an important part in evidence-based medicine or EBM. Adherence to EBM requires medical practitioners to keep abreast of the results of medical research as reported in their general and specialty journals. At the heart of this research is the science of statistics. It is through statistical techniques that researchers are able to discern the patterns in the data that tell a clinical story worth reporting. The authors begin by discussing samples and populations, issues involved in causality and causal inference, and ways of describing data. They then proceed through the major inferential techniques of hypothesis testing and estimation, providing examples of univariate and bivariate tests. The coverage then moves to statistical modeling, including linear and logistic regression and survival analysis. In a final chapter, a user-friendly introduction to some newer, cutting-edge, regression techniques will be included, such as fixed-effects regression and growth-curve modeling. A unique feature of the work is the extensive presentation of statistical applications from recent medical literature. Over 30 different articles are explicated herein, taken from such journals. With the aid of this primer, the medical researcher will also find it easier to communicate with the statisticians on his or her research team. The book includes a glossary of statistical terms for easy access. This is an important reference work for the shelves of physicians, nurses, nurse practitioners, physician's assistants, medical students, and residents. 

Alfred DeMaris earned a Ph.D. in sociology from the University of Florida in 1982 and a master's degree in statistics from Virginia Tech in 1987. He is currently professor of sociology and statistician for the Center for Family and Demographic Research at Bowling Green State University in Bowling Green, Ohio. His other statistical monographs are Logit Modeling: Practical Applications (Sage, 1992) and Regression with Social Data: Modeling Continuous and Limited Response Variables (Wiley, 2004). He has published another dozen articles and book chapters on statistical techniques as well as approximately 70 journal articles on topics in family social psychology. His work has appeared in Psychological Bulletin, Sociological Methods & Research, Social Forces, Social Psychology Quarterly, Journal of Marriage and Family, and Journal of Family Issues, among other venues. He was twice awarded the Hugo Beigel Award for the best empirical article in the Journal of Sex Research. He has been teaching statistics at the undergraduate and graduate levels for the past thirty years. Through his company, Statistical Insights, he does statistical consulting on a regular basis for individuals in the social and behavioral sciences as well as those in medicine and industry.

Steven Selman received his undergraduate degree in Engineering Physics at the University of Toledo. Following his medical school training at Case Western Reserve University he completed residencies both in General Surgery and Urology at University Hospitals of Cleveland. His research interest has principally been in the arena of urologic oncology and methodologies of urologic resident education. He has over 100 publications in the peer reviewed urologic literature. Currently, Dr. Selman serves both as residency Program Director and Chair of the Department of Urology at University of Toledo Medical Center.

---

Converting Data into Evidence: A Statistics Primer for the Medical Practitioner provides a thorough introduction to the key statistical techniques that medical practitioners encounter throughout their professional careers. These techniques play an important part in evidence-based medicine or EBM. Adherence to EBM requires medical practitioners to keep abreast of the results of medical research as reported in their general and specialty journals. At the heart of this research is the science of statistics. It is through statistical techniques that researchers are able to discern the patterns in the data that tell a clinical story worth reporting. The authors begin by discussing samples and populations, issues involved in causality and causal inference, and ways of describing data. They then proceed through the major inferential techniques of hypothesis testing and estimation, providing examples of univariate and bivariate tests. The coverage then moves to statistical modeling, including linear and logistic regression and survival analysis. In a final chapter, a user-friendly introduction to some newer, cutting-edge, regression techniques will be included, such as fixed-effects regression and growth-curve modeling. A unique feature of the work is the extensive presentation of statistical applications from recent medical literature. Over 30 different articles are explicated herein, taken from such journals. With the aid of this primer, the medical researcher will also find it easier to communicate with the statisticians on his or her research team. The book includes a glossary of statistical terms for easy access. This is an important reference work for the shelves of physicians, nurses, nurse practitioners, physician's assistants, medical students, and residents.