data_analysis

A Guide on Data Analysis

A book on data analysis, causal inference, and econometrics, written for readers with little to no prior background who want to develop both statistical intuition and practical R skills. The print edition is published by Springer Cham as a four-volume series, and this repository hosts the open online edition that the print volumes are drawn from.

Read it online: https://mike-data-analysis.share.connect.posit.cloud/

What the book covers

The online edition runs from descriptive statistics through inference, regression, and causal inference, with a strong emphasis on the methods that have come to define modern empirical practice.

• Foundations: descriptive statistics, basic inference, hypothesis testing, sampling, ANOVA.
• Regression: OLS, GLS, MLE, penalized, robust, partial least squares.
• Generalized linear and mixed models: logistic, count, hierarchical.
• Modeling workflow: variable transformation, imputation, model specification, variable selection.
• Effects and decomposition: marginal effects, moderation, mediation, prediction vs. estimation.
• Causal inference: difference-in-differences with the modern staggered estimators (Goodman-Bacon, Callaway-Sant’Anna, Sun-Abraham, de Chaisemartin-D’Haultfoeuille, Borusyak-Jaravel-Spiess), regression discontinuity (incl. rdrobust), interrupted time series, synthetic control, synthetic DiD, changes-in-changes, event studies, instrumental variables (incl. examiner designs and proxies), matching, and DAGs.
• Sensitivity and robustness: specification curves, Oster coefficient stability, Cinelli-Hazlett robustness value (sensemakr), Rosenbaum bounds.
• Workflow and reporting: experimental design, EDA, reproducibility, synthetic data, HPC.

Table of contents

The book is organized into five parts plus an appendix. This section is auto-generated by tools/build-toc.R on every push — do not edit by hand.

Part I. Foundations

1. Prerequisites
2. Descriptive Statistics
3. Basic Statistical Inference

Part II. Regression

4. Linear Regression
5. Non-Linear Regression
6. Generalized Linear Models
7. Discrete Choice and Limited Dependent Variables
8. Tweedie Regression
9. Linear Mixed Models
10. Nonlinear and Generalized Linear Mixed Models
11. Nonparametric Regression
12. Quantile Regression and Distributional Methods

Part III. Ramifications

13. Data
14. Time Series Analysis
15. Variable Transformation
16. Imputation (Missing Data)
17. Model Specification Tests
18. Variable Selection
19. Hypothesis Testing
20. Marginal Effects
21. Moderation
22. Mediation
23. Prediction and Estimation

Part IV. Causal Inference

24. Causal Inference

• A. Experimental Design

25. Experimental Design
26. Interference and Spillover Effects
27. Sampling
28. Survey and Response Quality
29. Analysis of Variance
30. Multivariate Methods

• B. Quasi-Experimental Design

31. Quasi-Experimental Methods
32. Regression Discontinuity
33. Temporal Discontinuity Designs
34. Synthetic Difference-in-Differences
35. Difference-in-Differences
36. Changes-in-Changes
37. Synthetic Control
38. Event Studies
39. Instrumental Variables
40. Matching Methods
41. Machine Learning for Causal Inference
42. Uplift Modeling and Heterogeneous Treatment Effects
43. Text as Data and NLP for Causal Inference

• C. Other Concerns

44. Endogeneity
45. Biases
46. Directed Acyclic Graphs
47. Controls

Part V. Miscellaneous

48. Reporting Your Analysis
49. Exploratory Data Analysis
50. Sensitivity Analysis and Robustness Checks
51. Replication and Synthetic Data
52. Differential Privacy
53. High-Performance Computing
54. Clustered and Robust Inference

Part VI. Structural Econometrics

55. Estimation Methods for Structural Models
56. Structural Econometrics and Demand Estimation
57. Dynamic Discrete Choice
58. Dynamic Games
59. Structural Models of Selection and Unobserved Heterogeneity
60. Production Functions and Productivity
61. Frontier and Efficiency Analysis
62. Markups, Market Power, and Mergers
63. Demand Systems
64. Structural Models of Auctions
65. Machine Learning and AI for Structural Estimation
66. Structural Models in Marketing
67. Branding and Brand Equity
68. Structural Models in Finance

Appendix

A. Appendix B. Bookdown cheat sheet

Print edition (Springer Cham, 2025)

The book is published in four volumes by Springer Cham:

Volume	Title	Identifier
1	Foundations of Data Analysis	DOI 10.1007/978-3-032-01858-8
2	Regression Techniques for Data Analysis	ISBN 978-3-032-01834-2
3	Advanced Modeling and Data Challenges	ISBN 978-3-032-01718-5
4	Experimental Design	ISBN 978-3-032-01838-0

How to cite

Nguyen, M. (2025). Foundations of Data Analysis (Vol. 1). Springer Cham. https://doi.org/10.1007/978-3-032-01858-8

@book{Nguyen2025Vol1,
  author    = {Nguyen, Mike},
  title     = {Foundations of Data Analysis},
  volume    = {1},
  year      = {2025},
  publisher = {Springer Cham},
  doi       = {10.1007/978-3-032-01858-8}
}

Citation entries for Volumes 2 to 4 are listed in the preface of the online edition.

Building locally

The book is built with bookdown and renders to HTML (gitbook), PDF (LuaLaTeX), and EPUB.

install.packages(c("bookdown", "rmarkdown"))
bookdown::render_book(input = "index.Rmd")

The PDF route requires a working LaTeX installation with LuaLaTeX. On Windows, TinyTeX or MiKTeX both work; on macOS, MacTeX; on Linux, TeX Live.

The repo uses renv for package version pinning. After cloning, run renv::restore() to recreate the package environment used by the book.

Repository layout

.
├── index.Rmd               # title page and preface
├── 02-50*.Rmd              # numbered chapters
├── _bookdown.yml           # book configuration
├── _output.yml             # output formats (gitbook, PDF, EPUB, bs4_book)
├── preamble.tex            # LaTeX preamble for the PDF build
├── *.bib                   # bibliographies (book.bib, references.bib, packages.bib, references1.bib)
├── images/                 # figures and cover art
├── data/                   # datasets used in examples
├── renv/, renv.lock        # pinned package environment
└── _book/                  # rendered output (git-ignored)

Files prefixed with _ (e.g., _06.01-...) are draft fragments not included in the live book.

Errata

Spotted an error or have a suggestion? Please open an issue on this repository.

Author

Mike Nguyen, mikenguyen.netlify.app, GitHub @mikenguyen13.

License

The online edition is released under CC BY-NC-SA 4.0. The print editions of Volumes 1 to 4 published by Springer Cham (2025) are not covered by this license; all rights to the print editions are reserved by the publisher. See LICENSE for the full notice.