Search
   >> Home >> Resources & support >> Stata news >> An Introduction to Stata for Health Researchers

An Introduction to Stata for Health Researchers


Order
Stata advertises itself as software for performing data management, statistics, and graphics. Any one text claiming to cover Stata as a whole usually performs strongly in the coverage of one, or at most two, of these topics. An Introduction to Stata for Health Researchers provides in-depth and insightful coverage of all three, and it manages this feat by focusing on only those topics that are useful for those involved in medical research.

The first nine (yes, nine!) chapters of the text are devoted to getting started and used to Stata and to the essentials of effective data management. Throughout this section, the author does a great job of putting himself in the shoes of the new user, leaving no key information unstated. The reader learns the intricacies of Stata’s windows, the importance of documentation, how to use do-files, how to get help (and more importantly, how to help yourself), the command syntax, working with datasets, and basic data management tasks such as merging and reshaping datasets.

Chapter 10 is devoted to summary statistics, tables, and simple tests, and chapter 11 provides a good introduction to the modern Stata graphics systems, again doing so with a good eye for the intended audience, i.e., the Stata newbie.

Although the book is billed as a Stata introduction, even the experienced Stata user will have much to gain from the biostatistical discussions of chapters 12–15. The usual topics for health researchers are covered: the analysis of stratified data via epitab and regression models; linear, logistic, and Poisson regression; survival analysis including Cox regression, standardized rates, and correlation/ROC analysis of measurements; just to name a few. In discussing these methods, the author does an excellent job of showing how these methods relate to each other, for example, the analysis of a stratified case–control study using both mhodds and logistic. Sometimes the methods agree exactly, and sometimes they don’t, and the text proceeds to explain the change in model assumptions leading to the differences.

The text concludes with some supplementary material on advanced topics, such as sample size calculations, simulation, some Stata programming concepts, and tips on caring for your data and maintaining reproducibility.

For further details or to order online, please visit the Stata Bookstore.

The Stata Blog: Not Elsewhere Classified Find us on Facebook Follow us on Twitter LinkedIn Google+ Watch us on YouTube