An ideal textbook for complete beginners―assumes no prior knowledge of statistics or coding.
“I love this book. More importantly, my students love this book.”―Anna Harvey, New York University
“With clear explanations, beautiful visuals, and engaging examples, DSS is the obvious choice for any student looking to build their data science tool kit.”—Molly Roberts, University of California, San Diego
Data Analysis for Social Science (DSS) is a more accessible version of Kosuke Imai's Quantitative Social Science (QSS), Princeton University Press, 2017.
Assuming no prior knowledge of statistics or coding and only minimal knowledge of math, DSS teaches the fundamentals of data analysis for social science while analyzing data from published research with the free and popular statistical program R.
It teaches how to measure, predict, and explain quantities of interest based on data.
In chapter 1, we start from the very beginning by familiarizing ourselves with RStudio and R and learning to load and make sense of data. (Full chapter available for free here.)
In chapter 2, we learn what causal effects are and how to estimate them using randomized experiments. We analyze data from Project STAR to answer: What is the effect of small classes on student performance?
In chapter 3, we learn about surveys and how to visualize and summarize the distribution of single variables as well as the relationship between two variables. We analyze data on the 2016 British referendum to answer: Who Supported Brexit?
In chapter 4, we learn how to predict outcomes using simple linear regression models. We analyze data from 170 countries to predict GDP growth using night-time light emissions as measured from space.
In chapter 5, we learn how to estimate causal effects using observational data. We analyze survey and electoral data to answer: What was the effect of Russian TV propaganda on the 2014 Ukrainian elections?
In chapter 6, we cover basic probability. We learn about random variables and their distributions, the distinction between population parameters and sample statistics, and the two large sample theorems that enable us to measure statistical uncertainty.
In chapter 7, we learn how to quantify the uncertainty in our empirical findings in order to draw conclusions at the population level. We complete some of the analyses we started in chapters 2 through 5.
- It includes CHEATSHEETS of statistical concepts and R.
- It includes TIPS with supplemental materials, such as additional explanations, answers to common questions, notes on best practices, and recommendations.
- It includes RECALLs reminding you of relevant information mentioned earlier in the book. These reminders are particularly helpful when the book is read only a few pages at a time, such as over the course of a semester.
- It clearly identifies sections with more advanced material so that readers can skip them if they so choose.
- Whenever a new core concept is introduced, in the margin you will find its definition repeated (displayed in red).
- Whenever a new piece of R code is introduced, in the margin you will find a brief overview of how it works with an example (displayed in a cyan-colored frame).
- It comes with real-world datasets from published social scientific studies and the code to analyze them.
- It comes with instructor materials such as sample syllabus, lecture slides, in-class exercises, additional real-world datasets, and additional exercises with solutions. Get your exam copy here and request access to instructor's materials here.
We sincerely hope our book is helpful to you!
About the authors: Elena Llaudet is Assistant Professor of Political Science at Suffolk University in Boston. Kosuke Imai is Professor of Government and of Statistics at Harvard University.