Chapter 1, RefresheR, reviews the aspects of R that subsequent chapters will assume knowledge of. Here, we learn the basics of R syntax, learn of R's major data structures, write functions, load data, and install packages.
Chapter 2, The Shape of Data, discusses univariate data. We learn about different data types, how to describe univariate data, and how to visualize the shape of this data.
Chapter 3, Describing Relationships, covers multivariate data. In particular, we learn about the three main classes of bivariate relationships and learn how to describe them.
Chapter 4, Probability, kicks off a new unit by laying its foundations. We learn about basic probability theory, Bayes' theorem, and probability distributions.
Chapter 5, Using Data to Reason about the World, discusses sampling and estimation theory. Through examples, we learn of the central limit theorem, point estimation, and confidence intervals.
Chapter 6, Testing Hypotheses, introduces the subject of Null Hypothesis Significance Testing (NHST). We learn of many popular hypothesis tests and their non-parametric alternatives. Perhaps most importantly, we gain a thorough understanding of the misconceptions and gotchas of NHST.
Chapter 7, Bayesian Methods, presents an alternative to NHST based on a more intuitive view of probability. We learn the advantages and drawbacks of this approach too.
Chapter 8, The Bootstrap, details another approach to NHST by using a technique called resampling. We learn of its advantages and shortcomings. In addition, this chapter serves as a great reinforcement of the material in chapters 5 and 6.
Chapter 9, Predicting Continuous Variables, kicks off our new unit on predictive analytics and thoroughly discusses linear regression. Before the chapter's conclusion, we learn all about the technique, when to use it, and what traps to look out for.
Chapter 10, Predicting Categorical Variables, introduces four of the most popular classification techniques. By using all four on the same examples, we gain an appreciation for what makes each technique shine.
Chapter 11, Predicting Changes with Time, closes our unit of predictive analytics by introducing the topics of time series analysis and forecasting. This ends with a firm foundation on one of the premier methods of time series forecasting.
Chapter 12, Sources of Data, begins the final unit detailing data analysis in the real world. This chapter is all about how to use different data sources in R. In particular, we learn how to interface with databases, and request and load JSON and XML via an engaging example.
Chapter 13, Dealing with Missing Data, details what missing data is, how to identify types of missing data, some not-so-great methods for dealing with them, and two principled methods for handling them.
Chapter 14, Dealing with Messy Data, introduces some of the snags of working with less-than-perfect data in practice. This includes checking for unexpected input, wielding regex, and verifying data veracity with assertr.
Chapter 15, Dealing with Large Data, discusses some of the techniques that can be used to cope with data sets larger than what can be handled swiftly without a little planning. The key components of this chapter are on parallelization and Rcpp.
Chapter 16, Working with Popular R Packages, acknowledges that we’ve already wielded a lot of popular packages in this unit, but this chapter fills in some of the gaps and introduces some of the most modern packages that make speed and ease of use a priority.
Chapter 17, Reproducibility and Best Practices, closes with the extremely important (but often ignored) topic of how to use R like a professional. This includes learning about tooling, organization, and reproducibility.
