Stata is one of the best and most user-friendly general statistics packages and is increasingly used in areas such as the social and health sciences. This guide introduces the reader to the program and explains how to use Stata efficiently for scientific analysis of quantitative data. A series of examples and exercises with real data guides the reader through data management, basic uni- and bivariate analyses as well as multivariate linear and binary regression. The book also deals with more advanced topics, such as illustrating results from interaction models.
The book is written for students who have no previous experience with statistical software, and is therefore suitable for methods courses at Bachelor level. It is also suitable for experienced users of other packages and for Stata users seeking an overview of the program’s basic functionality.
Kim Mannemar Sønderskov is an Associate Professor in the Department of Political Science and Government, Aarhus University.
Table of Contents
1. Introduction
2. Getting started with Stata and data: User interface and data inspection
3. Data manipulation i: Entering, deleting and documenting data
4. Data manipulation ii: Modification of existing variables
5. Univariate analyses
6. Common bivariate analyses
7. Constructing reflective indices
8. Linear regression with OLS
9. Assumptions and diagnostics for the linear model
10. Interaction in linear models: Estimation, interpretation and illustration
11. Logistic regression
Appendix A: More about the Results window
Appendix B: Evaluate coder reliability with -datasignature- and merge-
Appendix C: Vertical bar charts for univariate distribution with -catplot-
Appendix D: -prtest- to test univariate proportions
Appendix E: Multivariate analysis of categorical variables with table analysis
Appendix F: More about index construction
References
Index
