Today, data science involves an interesting mixture of area-specific content knowledge with quantitative methods and computing. Furthermore, one may find data scientists occupying positions in a variety of academic departments, from computer science to marketing, and also in a variety of different industries. Of course, being well established collectors of data, social scientists ranging from the political to the psychological often require as much use of modern data science tools as any other group of researchers. Yet social scientists do not typically obtain the same level of training in computing, mathematics and statistics as their peers in the natural and computing sciences. Hence the existence of this book.
In Quantitative Social Science the reader will learn about essential techniques from probability and statistics, predictive modeling, network analysis, data wrangling and visualization, and a few other related topics. The book is written with the needs of social scientists in mind, but this does not mean that the reader must come from a social science background to benefit from reading it. In fact, I believe that this book provides an excellent introduction to data science for almost anyone. This is because the author has masterfully balanced careful explanations of the quantitative theory with the practical computer implementation of the methods applied to real world data sets that many readers will find interesting and appealing.
In order to implement methods and provide the reader with hands on experience in analyzing real data, the author has adopted the R statistical computing platform. In Quantitative Social Science the reader will learn the basics of R and see the relevant R code written out in full. Additionally, there is a website where the reader can access and download data sets and R code.
When it comes to the use of R in Quantitative Social Science An Introduction, there is more than meets the eye. This is because Imai has used the R package swirl to create interactive tutorials in R that the reader can use to test both their understanding of the material covered and their R coding skills. In fact, associated with each chapter are swirl tutorials that carefully reinforce the material of the corresponding chapter. This is in addition to end-of-chapter exercises included in the book.
As I was working through the book, I discovered a problem with a couple of the corresponding data sets from the web site. Specifically, for some reason I could not download the twitter-senator data set, and there was a data set for which the column names did not correspond to those used in the book. These are minor problems, but they should be corrected.
The fact that Quantitative Social Science An Introduction is carefully written, detailed, and interactive makes it useful either as a textbook for a lecture course or for self-study. It truly is an excellent book and a pleasure to read and work through. I highly recommend the book to anyone looking for an introduction to data science.
Jason M. Graham is an assistant professor in the department of mathematics at the University of Scranton, Scranton, Pennsylvania. His current professional interests are in teaching applied mathematics and mathematical biology, and collaborating with biologists specializing in the collective behavior of groups of organisms.