betaFeedback

WorksMathematics

Semiparametric causal mediation analysis in cluster-randomized trials with post-treatment confounding

Abstract

Causal mediation analysis of cluster-randomized trials can reveal how interventions affect outcomes through individual and spillover pathways. Most existing methods target natural mediation effects under assumptions that exclude treatment-induced mediator–outcome confounding. We develop a semiparametric framework for interventional mediation effects that accommodates such confounding and within-cluster interference without requiring cross-world independence assumptions. We identify cluster-average and individual-average direct and indirect effects and decompose the indirect effect into individual and spillover components, distinguishing pathways through an individual's own mediator and those of other cluster members. These contrasts evaluate hypothetical interventions on the joint mediator distribution and can differ from treatment effects carried through individual causal pathways represented by natural effects, thereby providing an intervention-oriented perspective that complements natural effects. We derive efficient influence functions to construct estimators using cluster-level cross-fitting, characterize their multiple-robustness properties, and establish conditions for asymptotic normality and semiparametric efficiency. To facilitate implementation, we develop a lower-dimensional reparameterization that reduces the need for multivariate density estimation and integration and allows nuisance functions to be estimated using parametric models or machine learning. Simulation studies evaluate finite-sample performance, and an application to a cluster-randomized trial of cognitive behavioral therapy for chronic pain illustrates the proposed methods.

Introduction

Cluster-randomized trials, in which groups of individuals rather than individual participants are randomized to treatment conditions, are widely used to evaluate interventions in health, biomedical, and social science research. The primary analysis of a cluster-randomized trial typically assesses whether an intervention is effective by estimating its total effect on a final outcome (Hayes and Moulton, 2017; Li et al., 2025). The total effect alone, however, does not reveal the mechanisms through which the intervention operates. Causal mediation analysis complements this overall assessment by examining pathways through post-treatment intermediate variables, referred to as mediators [8]. By distinguishing indirect effects operating through the mediator from direct effects operating through other pathways, causal mediation analysis can deepen our understanding of how an intervention works and inform the design and refinement of future interventions.

A growing literature has investigated causal mechanisms in cluster-randomized trials. Relative to simpler individually randomized trials, mediation analysis in cluster-randomized trials is further complicated by within-cluster interference, under which one individual’s mediator may affect not only that individual’s own outcome but also the outcomes of other members of the same cluster. In the single-mediator setting, VanderWeele et al. [17] decomposed the natural indirect effect into an individual mediation effect, capturing pathways through an individual’s own mediator, and a spillover mediation effect, capturing pathways through the mediators of other individuals in the same cluster. Cheng and Li [2] established semiparametric efficiency theory for inferring these effect estimands and developed efficient estimators that accommodate data-adaptive machine-learning methods for nuisance modeling. Subsequent work has extended this literature to settings with multiple mediators. For two unordered mediators, Ohnishi and Li [12] decomposed the mediator-specific exit indirect effect [20] into exit individual and exit spillover mediation effects, thereby providing a finer characterization of individual and spillover pathways, and developed a Bayesian nonparametric approach for estimation and inference. Tong et al. [16] generalized these exit mediation effects to an arbitrary number of mediators without requiring a known causal ordering among them and constructed efficient debiased machine-learning estimators. Together, these developments have substantially expanded the range of causal mechanisms that can be studied in cluster-randomized trials. Existing methods, however, mostly focus on settings without treatment-induced confounding of the mediator–outcome relationship.

Treatment-induced mediator-outcome confounding arises when the treatment affects an intermediate post-treatment variable that, in turn, influences both the mediator and the outcome. In this setting, natural mediation effects are generally not identified under sequential ignorability assumptions, and identifying them requires additional unverifiable restrictions on counterfactual quantities [1, 21] (Tchetgen Tchetgen and VanderWeele 2014). One approach to this problem is to target the natural mediation effects and assess their sensitivity to the unidentified cross-world dependence between the potential mediator and the potential outcome. For example, Ohnishi et al. [13] developed a Bayesian sensitivity analysis framework for natural mediation effects in cluster-randomized trials subject to post-treatment confounding, using a Gaussian copula model to parameterize the residual dependence between counterfactual mediator and outcome under different treatment conditions. As a complementary approach, we target interventional analogues of natural mediation effects, which replace individual-specific natural mediator values with stochastic draws from treatment-specific mediator distributions [14, 18, 19]. In the independent data setting, these effects can be identified in the presence of observed treatment-induced mediator-outcome confounding under appropriate exchangeability and positivity conditions, without specifying the unidentified cross-world dependence required for natural effects [5, 7]. In cluster-randomized trials, an individual’s outcome may depend on both their own mediator and those of other cluster members, motivating interventions on the joint mediator distribution to assess how changes in marginal distributions and their dependence affect the outcomes. The resulting contrasts quantifies the potential value of hypothetical mediator interventions by comparing mean outcomes under treatment and control mediator distributions while holding treatment fixed, and can differ from the treatment effects carried through individual causal pathways that natural effects explain [11]. Interventional effects provide a complementary, intervention-oriented perspective on the role of mediators.

We seek to develop novel semiparametric methods for interventional mediation analysis in cluster-randomized trials with treatment-induced mediator-outcome confounding. Our contributions are threefold. First, we define interventional direct and indirect effects by drawing the within-cluster mediator vector from its treatment-specific distribution conditional on baseline information, and further decompose the interventional indirect effect into individual and spillover components operating through an individual’s own mediator and the mediators of other cluster members, respectively. The proposed estimands allow arbitrary within-cluster interference and accommodate both cluster-average and individual-average target populations through general cluster-level weighting [9]. To our knowledge, this is the first effort to address interventional effect estimands in the presence of mediator spillover. Second, we derive the efficient influence functions and construct cluster-level cross-fitted estimators that accommodate flexible nuisance estimation [3]. Exact bias decompositions characterize their multiple robustness properties. The estimators are consistent under the required multiple robustness conditions for the nuisance functions. And, when all nuisance estimators are consistent and the required product rate conditions hold, the estimators are asymptotically normal and semiparametrically efficient. Third, to facilitate practical implementation, we further develop a lower-dimensional reparameterization of the efficient influence function that replaces high-dimensional post-treatment confounder densities and integration over the full mediator vector with density ratios, treatment classifiers, univariate mediator densities, and conditional mean regressions. In particular, we adapt the augmented-classification approach of Rudolph et al. [15] to estimate the key density ratio without directly modeling the corresponding high-dimensional conditional densities. We establish corresponding robustness and efficiency results under compatibility conditions on the auxiliary regressions and examine both implementations in simulation studies. We illustrate the proposed methods in the PPACT cluster-randomized trial of cognitive behavioral therapy for chronic pain.

Notation, estimands and assumptions

Consider a cluster-randomized trial with KK clusters, indexed by i∈{1,…,K}i \in\{1,\ldots,K\}. Let NiN_i denote the size of cluster ii, and let Ai∈{0,1}A_i \in\{0,1\} denote its treatment assignment, with Ai=1A_i=1 indicating treatment and Ai=0A_i=0 indicating control. All individuals in a cluster receive the same assignment. Baseline information consists of cluster-level covariates Vi∈RdV×1V_i \in\mathbb{R}^{d_V \times1} and individual-level covariates Xij∈RdX×1X_{ij} \in\mathbb{R}^{d_X \times1}, for j∈{1,…,Ni}j \in\{1,\ldots,N_i\}. We also write Xi={Vi,Xi1,…,XiNi}X_i = \{V_i,X_{i1},\ldots,X_{iN_i}\} for the full baseline covariate information in the cluster, with Xi=[Xi1,…,XiNi]T∈RNidX×1X_i = [X_{i1},\ldots,X_{iN_i}]^T \in\mathbb{R}^{N_i d_X \times1}. After assignment, we observe post-treatment confounders Zij∈RdZ×1Z_{ij} \in\mathbb{R}^{d_Z \times1}, followed by a mediator Mij∈RM_{ij} \in\mathbb{R} and an outcome Yij∈RY_{ij} \in\mathbb{R}. ZijZ_{ij} may be affected by treatment and may, in turn, affect both the mediators and the outcomes. Denote Zi=[Zi1,…,ZiNi]T∈RNi×dZZ_i = [Z_{i1},\ldots,Z_{iN_i}]^T \in\mathbb{R}^{N_i \times d_Z}, Mi=[Mi1,…,MiNi]T∈RNi×1M_i = [M_{i1},\ldots,M_{iN_i}]^T \in\mathbb{R}^{N_i \times1}, and Yi=[Yi1,…,YiNi]T∈RNi×1Y_i = [Y_{i1},\ldots,Y_{iN_i}]^T \in\mathbb{R}^{N_i \times1}. For an individual jj, Mi(−j)∈R(Ni−1)×1M_{i(-j)} \in\mathbb{R}^{(N_i-1) \times1} denotes the mediators of all other individuals in the same cluster. The observed data for cluster ii are Oi={Ni,Ci,Ai,Zi,Mi,Yi}O_i = \{N_i,C_i,A_i,Z_i,M_i,Y_i\}. We suppress the cluster index “ii” when referring to a generic cluster, using a “∙\bullet” in its place for individual-level variables; for example, we write MM and M∙jM_{\bullet j} for MiM_i and MijM_{ij}.

Let Z∙j(a)Z_{\bullet j}(a) denote the post-treatment confounders for individual jj under cluster treatment a∈{0,1}a \in\{0,1\}, and let M∙j(a,z)M_{\bullet j}(a,z) denote the potential mediator when treatment is set to aa and the full cluster confounder vector is set to z={z∙j,z∙(−j)}z = \{z_{\bullet j},z_{\bullet(-j)}\}. Similarly, Y∙j(a,z,m)=Y∙j(a,z∙j,z∙(−j),m∙j,m∙(−j))Y_{\bullet j}(a,z,m) = Y_{\bullet j}(a,z_{\bullet j},z_{\bullet(-j)},m_{\bullet j},m_{\bullet(-j)}) is the potential outcome when treatment, confounders, and mediators are set to aa, zz, and m={m∙j,m∙(−j)}m = \{\mathbf{m}_{\bullet j}, \mathbf{m}_{\bullet(-j)}\}, respectively. Dependence on the full vectors zz and mm permits an individual’s outcome to depend on both their own and other cluster members’ post-treatment variables. The potential variables are indexed only by interventions within the same cluster, thereby excluding interference across clusters.

We assume composition: Y∙j(a,m)=Y∙j(a,Z(a),m)Y_{\bullet j}(a,m) = Y_{\bullet j}(a,Z(a),m) and M∙j(a)=M∙j(a,Z(a))M_{\bullet j}(a) = M_{\bullet j}(a,Z(a)), where Z(a)Z(a) and M(a)M(a) collect the corresponding potential variables over cluster members. Thus, an intervention on the mediators leaves the post-treatment confounders at their natural values under treatment aa. We also assume Y∙j(a)=Y∙j(a,Z(a),M(a))=Y∙j(a,Z(a),M(a,Z(a)))Y_{\bullet j}(a) = Y_{\bullet j}(a,Z(a),M(a)) = Y_{\bullet j}(a,Z(a),M(a,Z(a))), i.e., the potential outcome under treatment alone equals the potential outcome obtained by setting both post-treatment vectors to their natural values under that treatment.

To define interventional mediation effects, let G(a)G(a) be a random draw from the conditional distribution of M(a)M(a) given (C,N)(C,N). Conditional on (C,N)(C,N), we construct G(0)G(0) and G(1)G(1) to be independent of one another and of all potential variables. Each G(a)G(a) is drawn as a joint cluster mediator vector, allowing the dependence among its components under treatment aa. This construction extends stochastic mediator interventions for intermediate confounding to clustered data setting [5, 15]. Specifically, we define the interventional direct effect (IDE) and interventional indirect effect (IIE) by

IDE=h(θ(1,0),θ(0,0)),IIE=h(θ(1,1),θ(1,0)).\mathrm{IDE} = h(\theta(1,0),\theta(0,0)), \qquad\mathrm{IIE} = h(\theta(1,1),\theta(1,0)).

where hh is a known contrast function specifying the effect scale, and

θ(a,a′)=E[WN∑j=1NY∙j(a,G∙j(a′),G∙(−j)(a′))]E[W],for a,a′∈{0,1}.(1)\theta(a,a') = \frac{\mathbb{E}\left[\frac{W}{N}\sum_{j=1}^{N}Y_{\bullet j}\left(a,G_{\bullet j}(a'),G_{\bullet(-j)}(a')\right)\right]}{\mathbb{E}[W]}, \qquad\text{for } a,a' \in\{0,1\}. \tag*{(1)}

References

  1. [1]Chen Avin, Ilya Shpitser, and Judea Pearl. Identifiability of path-specific effects. In Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, pages 357–363, 2005.
  2. [2]Chao Cheng and Fan Li. Semiparametric causal mediation analysis of cluster-randomized trials for indirect and spillover effects. Biometrika, 82(1):ujag017, 2026.DOI
  3. [3]Victor Chernozhukov, Denis Chetverikov, Mert Demirer, Esther Duflo, Christian Hansen, Whitney Newey, and James Robins. Double/debiased machine learning for treatment and structural parameters. The Econometrics Journal, 21(1):1–68, 2018.
  4. [4]Lynn DeBar, Meghan Mayhew, Lindsay Benes, Allison Bonifay, Richard A Deyo, Charles R Elder, Francis J Keefe, Michael C Leo, Carmit McMullen, Ashli Owen-Smith, et al. A primary care–based cognitive behavioral therapy intervention for long-term opioid users with chronic pain: a randomized pragmatic trial. Annals of internal medicine, 175(1):46–55, 2022.DOI
  5. [5]Iván Díaz, Nima S. Hejazi, Kara E. Rudolph, and Mark J. van der Laan. Nonparametric efficient causal mediation with intermediate confounders. Biometrika, 108(3):627–641, 2021. doi: 10.1093/biomet/asaa085.DOI
  6. [7]Nima S. Hejazi, Kara E. Rudolph, Mark J. van der Laan, and Iván Díaz. Nonparametric causal mediation analysis for stochastic interventional (in)direct effects. Biostatistics, 24(3):686–707, 2023. doi: 10.1093/biostatistics/kxac002.DOI
  7. [8]Kosuke Imai, Luke Keele, and Dustin Tingley. A general approach to causal mediation analysis. Psychological Methods, 15(4):309–334, 2010. doi: 10.1037/a0020761.DOI
  8. [9]Brennan C Kahan, Fan Li, Andrew J Copas, and Michael O Harhay. Estimands in cluster-randomized trials: choosing analyses that answer the right question. International Journal of Epidemiology, 52(1):107–118, 2023.DOI
  9. [10]Fan Li, Jiaqi Tong, Xi Fang, Chao Cheng, Brennan C Kahan, and Bingkai Wang. Model-robust standardization in cluster-randomized trials. Statistics in medicine, 44(20-22):e70270, 2025.arxiv.org/abs/2505.19336
  10. [11]Caleb H. Miles. On the causal interpretation of randomised interventional indirect effects. Journal of the Royal Statistical Society Series B: Statistical Methodology, 85(4):1154–1172, 2023. doi: 10.1093/jrsssb/qkad066.DOI
  11. [12]Yuki Ohnishi and Fan Li. A bayesian nonparametric approach to mediation and spillover effects with multiple mediators in cluster-randomized trials. Journal of the American Statistical Association, 121(553):716–728, 2026.arxiv.org/abs/2411.03489
  12. [13]Yuki Ohnishi, Michael J Daniels, Lei Yang, and Fan Li. Identification and estimation of causal mechanisms in cluster-randomized trials with post-treatment confounding using bayesian nonparametrics. arXiv preprint arXiv:2510.16673, 2025.arxiv.org/abs/2510.16673
  13. [14]Maya L. Petersen, Sandra E. Sinisi, and Mark J. van der Laan. Estimation of direct causal effects. Epidemiology, 17(3):276–284, 2006. doi: 10.1097/01.ede.0000208475.99429.2d.DOI
  14. [15]Kara E Rudolph, Nicholas T Williams, and Ivan Diaz. Practical causal mediation analysis: extending nonparametric estimators to accommodate multiple mediators and multiple intermediate confounders. Biostatistics, page kxae012, 2024.DOI
  15. [16]Jiaqi Tong, Chao Cheng, and Fan Li. Causal mediation in cluster-randomized trials with multiple mediators: Spillover-aware decomposition, identification, and semiparametric efficient inference, 2026.arxiv.org/abs/2604.10710
  16. [17]Tyler J. VanderWeele, Guanglei Hong, Stephanie M. Jones, and Joshua L. Brown. Mediation and spillover effects in group-randomized trials: A case study of the 4rs educational intervention. Journal of the American Statistical Association, 108(502):469–482, 2013. doi: 10.1080/01621459.2013.779832.DOI
  17. [18]Tyler J. VanderWeele, Stijn Vansteelandt, and James M. Robins. Effect decomposition in the presence of an exposure-induced mediator–outcome confounder. Epidemiology, 25(2):300–306, 2014. doi: 10.1097/EDE.0000000000000034.DOI
  18. [19]Stijn Vansteelandt and Rhian M. Daniel. Interventional effects for mediation analysis with multiple mediators. Epidemiology, 28(2):258–265, 2017. doi: 10.1097/EDE.0000000000000596.DOI
  19. [20]Fan Xia and Kwun Chuen Gary Chan. Decomposition, identification and multiply robust estimation of natural mediation effects with multiple mediators. Biometrika, 109(4):1085–1100, 2022.DOI
  20. [21]Fan Xia and Kwun Chuen Gary Chan. Identification, semiparametric efficiency, and quadruply robust estimation in mediation analysis with treatment-induced confounding. Journal of the American Statistical Association, 118(542):1272–1281, 2023.

Paper details

vlnc:W_mxa3kngn
Version
v1 · latest
Published
Fresh — added to the Hub within the last 30 days
Added
License
CC BY 4.0
Usage

views · 0

downloads · 0

A view counts once per browser per day, a download each time the PDF is requested.

  • Mathematics

Not recorded for this paper

View statement
Looking for related papers…
Contents