Home  /  Bookstore  /  Statistics  /  Books on Stata  /  A Gentle Introduction to Stata

A Gentle Introduction to Stata

Author: Alan C. Acock
Publisher: Stata Press
Copyright: 2006
ISBN-13: 978-1-59718-009-2
Pages: 289; paperback
Price: $42.00
cover
New edition available

Comment from the Stata technical group

Alan C. Acock’s A Gentle Introduction to Stata is an ideal book for students and for those who have experienced other statistical software packages but are new to Stata. Acock leads the way for the reader who is just learning social statistics and has never before used a statistics software package. He first explains how to use the Stata GUI, use dialog boxes, and load Stata datasets before moving on to statistical analysis. Users who are familiar with other statistical software packages can use this book to quickly become fluent in Stata.

Acock emphasizes using dialog boxes when beginning in Stata because dialog boxes make finding options easier and show the Stata commands that will accomplish what the reader is after. Using dialog boxes is particularly helpful when learning the graphics system.

Instead of creating small, artificial datasets, Acock relies on real datasets—like the General Social Survey for 2002 and the National Survey of Youth (1997)—to illustrate the real-world application of statistics. Each chapter uses the datasets in examples and end-of-chapter exercises that will appeal to anyone in the social sciences, including economists, sociologists, and psychologists.

The first four chapters are geared toward the basics of using Stata: navigating the user interface, loading data into Stata, creating value and variable labels, saving results, and logging commands. The remainder of the book follows the outline of a typical introductory statistics course, beginning with single-variable descriptive statistics and graphs, such as pie graphs and histograms, and moving on to bivariate analysis of two categorical variables, including tables and chi-squared tests. Acock covers one- and two-sample t tests, as well as nonparametric alternatives like the rank-sum test and the median test. A chapter is devoted to bivariate analysis of continuous variables, including simple correlation, regression, Spearman's rho, Cronbach's alpha, and the kappa statistic of interrater agreement. Acock then covers one- and two-way ANOVA and repeated-measure designs, followed by a chapter on multiple regression and diagnostics. The final statistics chapter is devoted to logistic regression.

A Gentle Introduction to Stata is an excellent beginner’s guide for people new to Stata. The book would be particularly useful as a supplementary text for an introductory statistics course, allowing students to learn statistics in the classroom and Stata at home.

Note for Stata 10 users: The commands discussed in this book work the same in Stata 10 as they did in Stata 9, but some of the menus and dialog boxes may differ slightly.


Table of contents

Preface (pdf)
Support materials for the book
1 Getting started
1.1 Introduction
1.2 The Stata screen
1.3 Using an existing dataset
1.4 An example of a short Stata session
1.5 Conventions
1.6 Chapter summary
1.7 Exercises
2 Entering data
2.1 Creating a dataset
2.2 An example questionnaire
2.3 Develop a coding system
2.4 Entering data
2.4.1 Labeling values
2.5 Saving your dataset
2.6 Checking the data
2.7 Chapter summary
2.8 Exercises
3 Preparing data for analysis
3.1 Introduction
3.2 Plan your work
3.3 Create value labels
3.4 Reverse-code variables
3.5 Create and modify variables
3.6 Create scales
3.7 Save some of your data
3.8 Summary
3.9 Exercises
4 Working with commands, do-files, and results
4.1 Introduction
4.2 How Stata commands are constructed
4.3 Getting the command from the menu system
4.4 Saving your results
4.5 Logging your command file
4.6 Summary
4.7 Exercises
5 Descriptive statistics and graphs for a single variable
5.1 Descriptive statistics and graphs
5.2 Where is the center of a distribution?
5.3 How dispersed is the distribution?
5.4 Statistics and graphs—unordered categories
5.5 Statistics and graphs—ordered categories and variables
5.6 Statistics and graphs—quantitative variables
5.7 Summary
5.8 Exercises
6 Statistics and graphs for two categorical variables
6.1 Relationship between categorical variables
6.2 Cross-tabulation
6.3 Chi-squared
6.3.1 Degrees of freedom—optional
6.3.2 Probability tables—optional
6.4 Percentages and measures of association
6.5 Ordered categorical variables
6.6 Interactive tables
6.7 Tables—linking categorical and quantitative variables
6.8 Summary
6.9 Exercises
7 Tests for one or two means
7.1 Tests for one or two means
7.2 Randomization
7.3 Hypotheses
7.4 One-sample test of a proportion
7.5 Two-sample test of a proportion
7.6 One-sample test of means
7.7 Two-sample test of group means
7.7.1 Testing for unequal variances
7.8 Repeated-measures t test
7.9 Power analysis
7.10 Nonparametric alternatives
7.10.1 Mann–Whitney two-sample rank-sum test
7.10.2 Nonparametric alternative: median test
7.11 Summary
7.12 Exercises
8 Bivariate correlation and regression
8.1 Introduction to bivariate correlation and regression
8.2 Scattergrams
8.3 Plotting the regression line
8.4 Correlation
8.5 Regression
8.6 Spearman’s rho: rank-order correlation for ordinal data
8.7 Alpha reliability
8.8 Kappa as a measure of agreement for categorical data
8.9 Summary
8.10 Exercises
9 Analysis of variance (ANOVA)
9.1 The logic of one-way analysis of variance
9.2 ANOVA example
9.3 ANOVA example using survey data
9.4 A nonparametric alternative to ANOVA
9.5 Analysis of covariance
9.6 Two-way ANOVA
9.7 Repeated-measures design
9.8 Intraclass correlation—measuring agreement
9.9 Summary
9.10 Exercises
10 Multiple regression
10.1 Introduction
10.2 What is multiple regression?
10.3 The basic multiple regression command
10.4 Increment in R-squared: semipartial correlations
10.5 Is the dependent variable normally distributed?
10.6 Are the residuals normally distributed?
10.7 Regression diagnostic statistics
10.7.1 Outliers and influential cases
10.7.2 Influential observations: dfbeta
10.7.3 Combinations of variables may cause problems
10.8 Weighted data
10.9 Categorical predictors and hierarchical regression
10.10 Fundamentals of interaction
10.11 Summary
10.12 Exercises
11 Logistic regression
11.1 Introduction
11.2 An example
11.3 What are an odds ratio and a logit?
11.3.1 The odds ratio
11.3.2 The logit transformation
11.4 Data used in rest of chapter
11.5 Logistic regression
11.6 Hypothesis testing
11.6.1 Testing individual coefficients
11.6.2 Testing sets of coefficients
11.7 Nested logistic regressions
11.8 Summary
11.9 Exercises
12 What’s next?
12.1 Introduction
12.2 Resources
12.2.1 Web resources
12.2.2 Books on Stata
12.2.3 Short courses
12.2.4 Acquiring data
12.3 Summary
References