Stata: A Really Short Introduction

by Felix Bittmann

Overview

Stata is one of the most popular statistical software in the world and suited for all kinds of users, from absolute beginners to experienced veterans. This book offers a clear and concise introduction to the usage and the workflow of Stata. Included topics are importing and managing datasets, cleaning and preparing data, creating and manipulating variables, producing descriptive statistics and meaningful graphs as well as central quantitative methods, like linear (OLS) and binary logistic regressions and matching. Additional information about diagnostical tests ensures that these methods yield valid and correct results that live up to academic standards. Furthermore, users are instructed how to export results that can be directly used in popular software like Microsoft Word for seminar papers and publications. Lastly, the book offers a short yet focussed introduction to scientific writing, which should guide readers through the process of writing a first quantitative seminar paper or research report. The book underlines correct usage of the software and a productive workflow which also introduces aspects like replicability and general standards for academic writing. While absolute beginners will enjoy the easy to follow point-and-click interface, more experienced users will benefit from the information about do-files and syntax which makes Stata so popular. Lastly, a wide range of user-contributed software („Ados") is introduced which further improves the general workflow and guarantees the availability of state of the art statistical methods.

Product Details

ISBN-13:	9783110617290
Publisher:	De Gruyter
Publication date:	02/19/2019
Pages:	169
Product dimensions:	6.50(w) x 9.40(h) x 0.10(d)
Age Range:	18 Years

About the Author

Felix Bittmann, University of Bamberg

Table of Contents

List of Notes viii

1 Introduction 1

1.1 Formatting 1

1.2 Graphic style 2

1.3 Version info 3

1.4 Online resources 3

1.5 Cheat sheet 3

2 The first steps 4

2.1 The graphical user interface (GUI) 4

2.2 Opening stata files 5

2.3 Importing non-Stata file formats 7

2.4 Entering data manually 7

2.5 Using preinstalled data 8

2.6 Saving and exporting data 9

2.7 The basic workflow 10

2.8 Do-files 11

2.9 Delimit and line breaks* 14

3 Cleaning and preparing data 16

3.1 Getting to know your data 16

3.2 Variable names and labels 18

3.3 Labeling values 19

3.4 IDs and unique identifiers 21

3.5 Missing values 24

3.6 Creating new variables 26

3.6.1 Special functions 28

3.7 The if qualifier 30

3.8 Changing and replacing variables 32

3.9 Removing observations and variables 35

3.10 Cleaning data systematically 36

3.11 Combining datasets* 38

3.11.1 Appending datasets 38

3.11.2 One-to-One Merge 39

3.11.3 Many-to-One Merge 41

3.11.4 One-to-Many Merge 42

3.11.5 All pairwise combinations 42

3.12 Reshaping data* 43

4 Describing data 46

4.1 Summarizing information 47

4.2 Using stored results* 49

4.3 Histograms 51

4.4 Boxplots 53

4.5 Simple bar charts 55

4.6 Scatterplots 56

4.7 Frequency tables 58

4.8 Summarizing information by categories 61

4.9 Editing and exporting graphs 64

4.9.1 Combining graphs 65

4.10 Correlations 67

4.11 Testing for normality 68

4.12 t-test for groups* 69

4.13 Weighting* 71

5 Introduction to causal analysis 73

5.1 Correlation and causation 73

5.2 Causal graphs 74

5.3 Estimating causal effects 77

5.4 What does "controlling" actually mean?* 79

6 Regression analysis 83

6.1 Research question 83

6.2 What is a regression? 84

6.3 Binary independent variable 85

6.4 Ordinal independent variable 87

6.5 Metric independent variable 91

6.6 Interaction effects* 94

6.6.1 The classic way 96

6.6.2 Marginal effects 96

6.6.3 Predicted values 97

6.6.4 Separate analyses by subgroups 99

6.7 Standardized regression coefficients* 100

7 Regression diagnostics 102

7.1 Exogeneity 102

7.2 Random sampling 103

7.3 Linearity in parameters 103

7.3.1 Solutions 106

7.4 Multicollinearity 107

7.4.1 Solutions 108

7.5 Heteroscedasticity 108

7.5.1 Solutions 110

7.6 Influential observations 113

7.6.1 Dfbetas 114

7.6.2 Cook's distance 115

7.7 Summary 117

8 Logistic regression* 119

8.1 Introduction 119

8.2 Control variables 125

8.3 Nested Models 129

8.4 Diagnostics 130

8.4.1 Model misspecification 130

8.4.2 Sample size and empty cells 130

8.4.3 Multicollinearity 131

8.4.4 Influential observations 132

9 Matching 134

9.1 Simulating an experiment 134

9.2 Propensity score matching 135

9.3 Matching diagnostics 138

9.3.1 Common support 138

9.3.2 Balancing of covariates 139

10 Reporting results 141

10.1 Tables 141

10.2 Graphs 144

11 Writing a seminar paper 150

11.1 The basic structure 150

11.2 Master do-files 152

12 The next steps 153

12.1 Online sources and manuals 153

12.2 Books 153

References 155

Copyright 157

Index 158