This chapter covers compensating differentials, the theoretical foundation for most of the book. The key idea follows from Chapter 1's broad definition of compensation as “everything a worker likes about the job”. Jobs have many positive and negative characteristics, and workers vary in how much they value (or dislike) these characteristics. Positive job characteristics are a form of non-monetary pay, and negative characteristics diminish a worker’s effective pay. Holding other job characteristics constant, workers must be paid more to compensate them for a particular negative job characteristic and, similarly, are willing to accept less monetary pay when they enjoy a particular positive job characteristic. Workers sort across different jobs and employers based on their preferences for those job characteristics. The size of the wage differential (arising from a particular job characteristic) that occurs in the market is determined by the “marginal worker's” preferences for that job characteristic. Through a series of extensive examples, the reader is led to a thorough understanding of the marginal worker and compensating differentials, concepts which recur throughout the book.

Why you care: Statistics are fundamental to designing and analyzing experiments.

The book begins with three paradoxes of Libya, Venezuela, and Congo that juxtapose the profound importance of nationalization in the global natural resource economy with its economic risks and potential costs. The chapter then previews the answer to the puzzle of operational nationalization: when faced with the choice of nationalization, weak rulers discount the long-run costs of state intervention to seize its short-term gains; by contrast, strong leaders maintain the status quo of privately run operations to ensure long-term gains from private production. Next, the chapter illustrates the relevance of nationalization in a variety of research contexts: the effects of state intervention in the market; the roles of domestic leadership and international conditions in institutional choice; the significance of this choice during state formation; and the logic of the predatory state. After briefly introducing the theory of how, why, and when different operational nationalization pathways matter for politics, the chapter concludes by outlining how the remaining chapters of the book explain and test the operational nationalization theory.

This chapter connects pay to the important (and costly, from an organizational standpoint) subject of employee turnover. It opens by discussing how the level of pay relates to workers’ turnover rates. A discussion of the timing of compensation (over the course of the worker’s career or tenure with the employer) follows, the key point being that deferred compensation encourages retention. Employers might renege on deferred-pay contracts, which introduces risk for workers. The chapter covers workers’ perceptions of risk as they pertain to the timing and design of pay and to sorting effects. When pay is deferred, workers sometimes advance to a career stage in which their pay outpaces their productivity, at which time employers would like them to quit. Inducing workers to leave can be tricky, particularly given the external and internal constraints covered in Chapters 4 and 5. Sections 12.5 and 12.6 concern severance packages and buyouts, which basically involve paying workers to leave. The conditions under which such payments are offered and accepted are covered. The chapter ends with coverage of corporate raids and when a manager should match an outside offer received by an employee.

There are many tools and techniques that a data scientist is expected to know or acquire as problems arise. Often, it is hard to separate tools and techniques. One whole section of this book (four chapters) is dedicated to teaching how to use various tools, and, as we learn about them, we also pick up and practice some essential techniques. This happens for two reasons. The first one is already mentioned here – it is hard to separate tools from techniques. Regarding the second reason – since our main purpose is not necessarily to master any programming tools, we will learn about programming languages and platforms in the context of solving data problems.

Why you care: The choice of randomization unit is critical in experiment design, as it affects both the user experience as well as what metrics can be used in measuring the impact of an experiment. When building an experimentation system, you need to think through what options you want to make available. Understanding the options and the considerations to use when choosing amongst them will lead to improved experiment design and analysis.

This chapter presents a detailed example that applies the compensation analytics concepts developed in Chapter 6. The reader is assumed to be a compensation consultant charged with evaluating whether gender-based discrimination in pay is present in a public university system in the sciences. Section 7.1 walks through the analysis step-by-step, from formulating the business question, to acquiring and cleaning data, to analyzing the data and interpreting the results from voluminous statistical output in light of the business question. Section 7.2 covers exploratory data mining, causality, and experiments. Exploratory data mining covers situations in which the manager does not know in advance which relationships in the data will be of interest, in contrast to the example in section 7.1 in which a statistical model and specific measures could be constructed that were directly tailored to address the business question at hand. Section 7.2 covers the challenges associated with establishing causality in compensation research and how experiments can sometimes be designed to address those challenges. Randomization and some pitfalls associated with compensation experiments are also covered