Health Services Research Using SAS

I have read hundreds of SAS(R) books and manuals in my career as a researcher and teacher. Most provide important rules of the road or “Sasoids”, a phrase coined by Andy Ravenna an instructor at the New York SAS(R) Training Center. Since1980, they include manuals for all of the software releases from Version 4 in the1980s through Version 9 in 2008. Each serves as a resource to answer a coding question. In addition, SAS(R) provides on line help that codifies all of the coding questions with examples and syntax. These can be found on your help screen of you current SAS(R) release or at www.support.sas.com. I must confess that the book that I have had on the side of my computer since 1996 for quick answers The Little Book SAS(R), by Delwiche DL and Slaughter, SJ, today in its Fifth Edition. In addition, I use Google as an invaluable resource for SAS syntax. Health Services Research Using SAS(R) also contains SAS rules and tools in Chapters 1 and 2. However, Chapter 3, 4 and 5 have real health care data from public sources such as the National Center for Health Statistics, National Hospital Discharge Survey, www.cdc.gov/nchs, the Organ Procurement and Transplantation Network, www.optn.transplat.hersa.gov and the California Office of Statewide Health Planning and Development (OSPHD) www.oshpd.ca.gov. Within each of these chapters is the history of the data sets, the organizational structure of the respective agencies, their mission and goals, and their published findings. Following the historical perspective chapters, SAS(R) coding is introduced for the analysis of the above data sets. All of the code uses best practices, learned from the faculty at New York SAS(R) Training Center. In addition, the scope and sequencing used in the courses includes exploratory data analysis (EDA), creating libraries, formatting, labels, indicator variables, truth logic, multivariate analysis, linear and logistic, and survival analysis. Each of these chapters selects an area of interest. For example, using the National Discharges Survey, you can identify the nations most common discharge diagnoses and procedures and compare the most common discharge diagnoses and procedures between the uninsured and insured. You can use the OPTN/UNOS data for the 88,636 liver transplants occurring in the U.S., between 1987 and 2008, present the demographic and clinical measurements for these transplants, identifying the factors that influence survival time. For the homeless who use California emergency departments (ED), you can show the most common discharge diagnoses and measure if age of the California homeless is influenced by gender, race, ethnicity, payer, disposition and county. All SAS(R) output is included which allows findings and results to be discussed. In addition each chapter has exercises and their corresponding answers. Before buying this book, your skills should include: (1) a strong understanding of statistical methods obtained in an undergraduate or graduate course. (2) familiarity with clinical coding methods such as the ICD-9-CM diagnosis and procedures and (3) function as an intermediate SAS(R) coder, and/or with experience in STATA, R, IBM SPSS or any of the numerous statistical packages listed on https//en.wikipedia.org/wiki/List_of statistical_packages.