Data Visualization and Analysis in Second Language Research

Guilherme D. Garcia is Assistant Professor of Linguistics at Ball State University, USA.

Contents

List of figures

List of tables

List of code blocks

Acknowledgments

Preface

Part I Getting ready

1 Introduction

1.1 Main objectives of this book

1.2 A logical series of steps

1.2.1 Why focus on data visualization techniques?

1.2.2 Why focus on full-fledged statistical models?

1.3 Statistical concepts

1.3.1 p-values

1.3.2 Effect sizes

1.3.3 Confidence intervals

1.3.4 Standard errors

1.3.5 Further reading

2 R basics 23

2.1 Why R?

2.2 Fundamentals

2.2.1 Installing R and RStudio

2.2.2 Interface

2.2.3 R basics

2.3 Data frames

2.4 Reading your data

2.4.1 Is your data file ready?

2.4.2 R Projects

2.4.3 Importing your data

2.5 The tidyverse package

2.5.1 Wide-to-long transformation

2.5.2 Grouping, filtering, changing, and summarizing data

2.6 Figures

2.6.1 Using ggplot2

2.6.2 General guidelines for data visualization

2.7 Basic statistics in R

2.7.1 What’s your research question?

2.7.2 t-tests and ANOVAs in R

2.7.3 A post-hoc test in R

2.8 More packages

2.9 Additional readings on R

2.10 Summary

2.11 Exercises

Part II Visualizing the data

3 Continuous data

3.1 Importing your data

3.2 Preparing your data

3.3 Histograms

3.4 Scatter plots

3.5 Box plots

3.6 Bar plots and error bars

3.7 Line plots

3.8 Additional readings on data visualization

3.9 Summary

3.10 Exercises

4 Categorical data

4.1 Binary data

4.2 Ordinal data

4.3 Summary

4.4 Exercises

5 Aesthetics: optimizing your figures

5.1 More on aesthetics

5.2 Exercises

Part III Analyzing the data 127

6 Linear regression 129

6.1 Introduction

6.2 Examples and interpretation

6.2.1 Does Hours affect scores?

6.2.2 Does Feedback affect scores?

6.2.3 Do Feedback and Hours affect scores?

6.2.4 Do Feedback and Hours interact?

6.3 Beyond the basics

6.3.1 Comparing models and plotting estimates

6.3.2 Scaling variables

6.4 Summary

6.5 Exercises

7 Logistic regression

7.1 Introduction

7.1.1 Defining the best curve in a logistic model

7.1.2 A family of models

7.2 Examples and interpretation

7.2.1 Can reaction time differentiate learners and native speakers?

7.2.2 Does Condition affect responses?

7.2.3 Do Proficiency and Condition affect responses?

7.2.4 Do Proficiency and Condition interact?

7.3 Summary

7.4 Exercises

8 Ordinal regression

8.1 Introduction

8.2 Examples and interpretation

8.2.1 Does Condition affect participants’ certainty?

8.2.2 Do Condition and L1 interact?

8.3 Summary

8.4 Exercises

9 Hierarchical models

9.1 Introduction

9.2 Examples and interpretation

9.2.1 Random-intercept model

9.2.2 Random-slope and random-intercept model

9.3 Additional readings on regression models

9.4 Summary

9.5 Exercises

10 Going Bayesian

10.1 Introduction to Bayesian data analysis

10.1.1 Sampling from the posterior

10.2 The RData format

10.3 Getting ready

10.4 Bayesian models: linear and logistic examples

10.4.1 Bayesian model A: Feedback

10.4.2 Bayesian model B: Relative clauses with prior specifications

10.5 Additional readings on Bayesian inference

10.6 Summary

10.7 Exercises

11 Final remarks

Appendix A: Troubleshooting

Appendix B: RStudio shortcuts

Appendix C: Symbols and acronyms

Appendix D: Files used in this book

Appendix E: Contrast coding

Appendix F: Models and nested data

Glossary

References

Subject index

Function Index