Search results

The purpose of this chapter is to illustrate the identification problem involved in estimating the impact of military service on labor-market outcomes and to review the modern literature in economics which aim to estimate this effect. Drawing from the literature on microeconometric treatment evaluation, the existence of a selection bias is demonstrated and a discussion of empirical strategies to overcome this is presented. Studies on the effect of military service in the United States, Germany, the Netherlands, Portugal, and the United Kingdom are discussed. The main results of each reviewed article are presented. There is substantial heterogeneity in the estimated impacts of military service on labor-market outcomes. The results may not be generalizable to the general population due to the econometric methods employed. Moreover, the literature review is concentrated on the contribution of economists to this issue and neglects to discuss research conducted by other social scientists. The studies are varied and located in different journals. This review serves to summarize the results in one article. Furthermore, the technical discussion on methods will be useful for those who wish to pursue the topic further. This chapter provides practical advice on how to credibly estimate treatment effects based on nonexperimental data. It also facilitates future reviews of the topic by collecting the available evidence.

A discipline is bound by some combination of a shared subject matter, shared theory, and shared technique. Yet modern economics is seemingly without limit to its domain. As a discipline without a shared subject matter, what is the binding force of economics today? The authors combine topic modeling and text analysis to analyze different approaches to inquiry within the discipline of economics. The authors find that the importance of theory has declined as economics has increasingly become defined by its empirical techniques. The authors question whether this trajectory is stable in the long run as the binding force of the discipline.

The growing displacement of theory and other forms of wide-ranging knowledge of social phenomena by empirical research methods in economics is widely noted by economists and historians of economic knowledge. Less attention has been devoted, however, to understand the materialization of such changes in the scientific practices. This article studies the recent transformations in the epistemological practices at CEDE, a research center in Colombia. I use a machine learning technique called Topic Modeling, interviews to CEDE researchers, and exegesis of papers to characterize a shift in the production of knowledge in microeconometrics at CEDE during the years 2000 and 2018. I explain this shift by characterizing two sets of epistemological practices that implies a recent tendency to disdain research that cannot make a “strong” causal inference.

We discuss the two most popular frameworks for identification, estimation and inference in regression discontinuity (RD) designs: the continuity-based framework, where the conditional expectations of the potential outcomes are assumed to be continuous functions of the score at the cutoff, and the local randomization framework, where the treatment assignment is assumed to be as good as randomized in a neighborhood around the cutoff. Using various examples, we show that (i) assuming random assignment of the RD running variable in a neighborhood of the cutoff implies neither that the potential outcomes and the treatment are statistically independent, nor that the potential outcomes are unrelated to the running variable in this neighborhood; and (ii) assuming local independence between the potential outcomes and the treatment does not imply the exclusion restriction that the score affects the outcomes only through the treatment indicator. Our discussion highlights key distinctions between “locally randomized” RD designs and real experiments, including that statistical independence and random assignment are conceptually different in RD contexts, and that the RD treatment assignment rule places no restrictions on how the score and potential outcomes are related. Our findings imply that the methods for RD estimation, inference, and falsification used in practice will necessarily be different (both in formal properties and in interpretation) according to which of the two frameworks is invoked.