To understand the patterns and trends of various forms of inequality, quantitative social science research has typically relied on statistical models linking the conditional mean of an outcome of interest to a range of explanatory factors. A prime example of this approach is the widely used Kitagawa-Oaxaca-Blinder (KOB) method. By fitting two linear models separately for an advantaged group and a disadvantaged group, the KOB method decomposes the between-group outcome disparity into two parts, a part explained by group differences in a set of background characteristics and an unexplained part often dubbed “residual inequality.” In this paper, we explicate and contrast two distinct approaches to studying group disparities, which we term the descriptive approach, as epitomized by the KOB method and its variants, and the prescriptive approach, which focuses on how a disparity of interest would change under a hypothetical in- tervention to one or more manipulable treatments. For the descriptive approach, we propose a generalized KOB decomposition
that considers multiple (sets of) explanatory variables sequen- tially. For the prescriptive approach, we introduce a variety of stylized interventions, such as lottery-type and affirmative-action-type
interventions that close between-group gaps in treat- ment. We illustrate the two approaches to disparity analysis by assessing the Black-White gap in college completion,
how it is statistically explained by racial differences in demographic and socioeconomic background, family structure, ability and behavior, and college selectivity,
and the extent to which it would be reduced under hypothetical reallocations of college-goers from different racial/economic backgrounds into different tiers of college --- reallocations that could be targeted by race- or class-conscious admissions policies.
Zhou, Xiang, and Aleksei Opacic. Marginal Interventional Effects.
Reject & Resubmit at Statistical Science
[Abstract]
Conventional causal estimands, such as the average treatment effect (ATE), reflect how the mean outcome in a population or subpopulation would change if all units received treatment versus control. Real-world policy changes, however, are often incremental, changing the treatment status for only a small segment of the population who are at or near “the margin of participation.” To capture this notion, two parallel lines of inquiry have developed in economics and in statistics and epidemiology that define, identify, and estimate what we call interventional effects. In this article, we bridge these two strands of literature by defining interventional effect (IE) as the per capita effect of a treatment intervention on an outcome of interest, and marginal interventional effect (MIE) as its limit when the size of the intervention approaches zero. The IE and MIE can be viewed as the unconditional counterparts of the policy-relevant treatment effect (PRTE) and marginal PRTE (MPRTE) proposed in the economics literature. However, different from PRTE and MPRTE, IE and MIE are defined without reference to a latent index model, and, as we show, can be identified either under unconfoundedness or through the use of instrumental variables. For both scenarios, we show that MIEs are typically identified without the strong positivity assumption required of the ATE, highlight several “stylized interventions” that may be of particular interest in policy analysis, discuss several parametric and semiparametric estimation strategies, and illustrate the proposed methods with an empirical example.
Opacic, Aleksei. Monotonic Path-Specific Effects: Application to Estimating Educational Returns.
[Abstract]
Conventional research on educational effects typically either employs a “years of schooling” measure of education, or dichotomizes attainment as a point-in-time treatment. Nevertheless, such a conceptualization of education is at odds with the sequential process by which individuals make educational transitions. In this paper, I propose a causal mediation framework for the study of educational effects on outcomes such as earnings. The framework considers the effect of a given educational transition as operating indirectly, via progression through subsequent transitions, as well as directly, net of these transitions. I demonstrate that the average treatment effect (ATE) of education can be additively decomposed into mutually exclusive components that capture these direct and indirect effects. The decomposition has several special properties which distinguish it from conventional mediation decompositions of the ATE, properties which facilitate less restrictive identification assumptions as well as identification of all causal paths in the decomposition. An analysis of the returns to high school completion in the NLSY97 cohort suggests that the payoff to a high school degree stems overwhelmingly from its direct labor market returns. Mediation via college attendance, completion and graduate school attendance is small because of individuals' low counterfactual progression rates through these subsequent transitions.
Working papers
-
Blackwell, Matthew, Ruofan Ma and Aleksei Opacic. Assumption Smuggling in Intermediate Outcome Tests of Causal Mechanisms.
[Abstract]
Political scientists are increasingly attuned to the promises and pitfalls of establishing causal effects. But the vital question for many is not if a causal effect exists but why and how it exists. Even so, many researchers avoid causal mediation analyses due to the assumptions required, instead opting to explore causal mechanisms through what we call intermediate outcome tests. These tests use the same research design used to estimate the effect of treatment on the outcome to estimate the effect of the treatment on one or more mediators, with authors often concluding that evidence of the latter is evidence of a causal mechanism. We show in this paper that, without further assumptions, this can neither establish nor rule out the existence of a causal mechanism. Instead, such conclusions about the indirect effect of treatment rely on implicit and usually very strong assumptions that are often unmet. Thus, such causal mechanism tests, though very common in political science, should not be viewed as a free lunch but rather should be used judiciously, and researchers should explicitly state and defend the requisite assumptions.
-
Opacic, Aleksei. Mothers and Mobility: a Re-examination of (Trends in) Intergenerational Mobility in the UK
[Abstract]
Existing research on intergenerational class mobility typically uses either fathers’ occupation, or the occupation of the ‘class dominant’ parent, as an indicator of ‘class origin’, ignoring heterogeneity in mothers’ and fathers’ class effects on children’s mobility outcomes. Such an elision therefore misses how class reproduction may be shaped by gender in important ways. In this paper, I bring new empirical evidence to the role of mothers in intergenerational mobility in Britain for birth cohorts born in the latter half of the 20th century. I find a significant independent effect of mothers’ class on individuals’ class destinations, and evidence that fathers’ and mothers’ class positions show a stronger effect on same-gender children. Further, mothers and fathers’ class effects do not show similar trends across cohorts; while fathers’ effects have weakened for women but stayed constant for men, mothers’ effects have weakened for both men and women. My findings highlight the importance of taking a gender-sensitive approach to the study of intergenerational mobility patterns and trends.
- Opacic, Aleksei. Does Higher Education Tend Towards Egalitarianism? Evidence from a Population Transitions Model
[Abstract]
Many scholars characterize educational attainment as a process that “tends towards egalitarianism” across the life course, based on the highly-replicated finding that family background effects on attainment appear to decline across educational transitions. Yet, such descriptive transitions models typically measure disparities at a given educational level among only the “survivors” of all prior transitions. By ignoring lower-income students’ over-selection into different educational stages, these approaches arguably fail to capture aspects of educational inequality arguably of greatest theoretical and policy interest. By proposing a population transitions model via a potential outcomes framework, I ask how educational inequality would evolve counterfactually over the life course for the entire high school-going population. Drawing on data from the NLSY97, I challenge the notion that individuals are decreasingly constrained by social origin over the educational life course: while only 35% of individuals from the lowest parental income group are expected to graduate college, that same figure is 77% for individuals from the highest parental income group. More straightforwardly, BA inequalities parallel inequalities in high school completion, a constancy across transitions not revealed by descriptive models. To highlight the policy implications of these results, I estimate hypothetical BA attainment inequalities under different degrees of college seat expansion. Contrary to expectations from descriptive transitions models, I show that even extreme higher-educational expansion would do little to reduce BA inequalities overall.