This book provides an introduction to statistics and data analysis using Stata, a
statistical software package. It is intended to serve as a textbook for undergraduate courses in business, economics, sociology, political science, psychology, criminal justice, public health, and other fields that involve data analysis. However, it could also be useful in an introductory graduate course or for researchers interested in
learning Stata.
The book was developed out of our experience in teaching statistics and data analysis
to undergraduate students over 20 years, as well as giving training courses in Stata
and survey methods in more than a dozen countries. Based on these experiences, we
have included three features that we feel are an integral part of data analysis. First,
the book provides an introduction to research design and data collection, including
questionnaire design, sample selection, sampling weights, and data cleaning. These
topics are an essential part of empirical research and provide students with the skills
to conduct their own research and evaluate research carried out by others. Second,
we emphasize the use of code or command files in Stata rather than the “point and
click” menu features of the software. We believe that students should be taught to
write programs that document their analysis, as this allows them to reproduce their
work during follow-up analyses and facilitates collaborative work (we do, however,
include brief instructions on the use of Stata menus for each command). Third, the
book teaches students how to describe statistical results for technical and nontechnical audiences. Choosing the correct statistical tests and generating results is useless
unless the researcher can explain the results to various audiences.