arXiv subjects

Felix Elwert

Publications and source records attributed to Felix Elwert.

5 recordsLinked to original sources

arXiv2026

Causal Overlap Effects: A Cumulative Fixed Effect Approach

Social scientists often ask about the effect of increasing one's duration of exposure to a social context on one's outcomes, i.e. the overlap effect. Past studies adopted a unidimensional treatment effect framework to estimate the effect of overlap, imposing important restrictions. In this paper, we propose a new causal framework of multidimensional treatments where the overlap effects include both the duration and the content of overlap, under which, for instance, the grandparent overlap effect is defined as the union of all causal effects of a grandparent's observed and unobserved characteristics (i.e., the content) on the grandchild across their shared life course (i.e., the duration). The multidimensional framework allows for a more flexible and context rich approach to effect heterogeneity, where unobserved contextual characteristics play two roles as unobserved confounders and as integral components of overlap effects -- overlap effects in this framework are not easily estimated with conventional fixed effects estimation. Hence, we develop a new cumulative fixed effects (CFE) approach that can estimate a range of interesting heterogeneous causal overlap effects from three-wave individual panel data. We show that the CFE approach is unbiased even in highly non-linear simulations, and we discuss assumptions and extensions.

econ.EM↗

arXiv2024

Detecting and Understanding the Difference between Natural Mediation Effects and Their Randomized Interventional Analogues

In causal mediation analysis, the natural direct and indirect effects (natural effects) are nonparametrically unidentifiable in the presence of treatment-induced confounding, which motivated the development of randomized interventional analogues (RIAs) of the natural effects. Being easier to identify, the RIAs are becoming widely used in practice. However, applied researchers often interpret RIA estimates as if they were the natural effects, even though the RIAs can be poor proxies for the natural effects. This calls for practical and theoretical guidance on when the RIAs differ from or coincide with the natural effects. We develop the first empirical test to detect the divergence between the natural effects and their RIAs under the weak assumptions sufficient for identifying the RIAs and illustrate the test using the Moving to Opportunity Study. We also provide new theoretical insights on the relationship between the natural effects and the RIAs both using a covariance formulation and from a structural equation perspective. This analysis also reveals previously undocumented connections between the natural effects, the RIAs, and estimands in instrumental variable analysis and Wilcoxon-Mann-Whitney tests.

stat.ME↗

arXiv2023

Nonparametric Causal Decomposition of Group Disparities

We introduce a new nonparametric causal decomposition approach that identifies the mechanisms by which a treatment variable contributes to a group-based outcome disparity. Our approach distinguishes three mechanisms: group differences in 1) treatment prevalence, 2) average treatment effects, and 3) selection into treatment based on individual-level treatment effects. Our approach reformulates classic Kitagawa-Blinder-Oaxaca decompositions in causal and nonparametric terms, complements causal mediation analysis by explaining group disparities instead of group effects, and isolates conceptually distinct mechanisms conflated in recent random equalization decompositions. In contrast to all prior approaches, our framework uniquely identifies differential selection into treatment as a novel disparity-generating mechanism. Our approach can be used for both the retrospective causal explanation of disparities and the prospective planning of interventions to change disparities. We present both an unconditional and a conditional decomposition, where the latter quantifies the contributions of the treatment within levels of certain covariates. We develop nonparametric estimators that are $\sqrt{n}$-consistent, asymptotically normal, semiparametrically efficient, and multiply robust. We apply our approach to analyze the mechanisms by which college graduation causally contributes to intergenerational income persistence (the disparity in adult income between the children of high- vs low-income parents). Empirically, we demonstrate a previously undiscovered role played by the new selection component in intergenerational income persistence.

stat.ME↗

arXiv2021

Estimating Sibling Spillover Effects with Unobserved Confounding Using Gain-Scores

A growing area of research in epidemiology is the identification of health-related sibling spillover effects, or the effect of one individual's exposure on their sibling's outcome. The health and health care of family members may be inextricably confounded by unobserved factors, rendering identification of spillover effects within families particularly challenging. We demonstrate a gain-score regression method for identifying exposure-to-outcome spillover effects within sibling pairs in a linear fixed effects framework. The method can identify the exposure-to-outcome spillover effect if only one sibling's exposure affects the other's outcome; and it identifies the difference between the spillover effects if both siblings' exposures affect the others' outcomes. The method fails in the presence of outcome-to-exposure spillover and outcome-to-outcome spillover. Analytic results and Monte Carlo simulations demonstrate the method and its limitations. To exercise this method, we estimate the spillover effect of a child's preterm birth on an older sibling's literacy skills, measured by the Phonological Awarenesses Literacy Screening-Kindergarten test. We analyze 20,010 sibling pairs from a population-wide, Wisconsin-based (United States) birth cohort. Without covariate adjustment, we estimate that preterm birth modestly decreases an older sibling's test score (-2.11 points; 95% confidence interval: -3.82, -0.40 points). In conclusion, gain-scores are a promising strategy for identifying exposure-to-outcome spillovers in sibling pairs while controlling for sibling-invariant unobserved confounding in linear settings.

stat.ME↗

arXiv2020

Instrumental Variables with Treatment-Induced Selection: Exact Bias Results

Instrumental variables (IV) estimation suffers selection bias when the analysis conditions on the treatment. Judea Pearl's early graphical definition of instrumental variables explicitly prohibited conditioning on the treatment. Nonetheless, the practice remains common. In this paper, we derive exact analytic expressions for IV selection bias across a range of data-generating models, and for various selection-inducing procedures. We present four sets of results for linear models. First, IV selection bias depends on the conditioning procedure (covariate adjustment vs. sample truncation). Second, IV selection bias due to covariate adjustment is the limiting case of IV selection bias due to sample truncation. Third, in certain models, the IV and OLS estimators under selection bound the true causal effect in large samples. Fourth, we characterize situations where IV remains preferred to OLS despite selection on the treatment. These results broaden the notion of IV selection bias beyond sample truncation, replace prior simulation findings with exact analytic formulas, and enable formal sensitivity analyses.

econ.EM↗