Causal Inference for Sequential Settings under Interference and Latent Confounding
Abstract
We study causal inference under outcome interference for sequential, observational settings. Specifically, we consider settings where the binary outcomes over N units are Markovian across T time steps. At each time step, the outcomes of N units have dependencies captured through an Ising model; each outcome is also impacted through an external field capturing the effects of its treatment as well as latent confounders. Similar to panel data literature, these latent confounders are modeled to have a low-rank factor structure. Our data is a single sample from this high-dimensional distribution. To estimate causal quantities of interest, we provide a computationally efficient method based on Maximum Pseudo-Likelihood Estimation (MPLE) for learning the model parameters. Under mild assumptions, we establish non-asymptotic consistency for parameter estimation and show this translates to faithful estimation of causal quantities of interest after sampling from the learned model. We demonstrate the efficacy of the method through synthetic experiments as well as a real-world case-study investigating causal effects of vaccine rates on COVID-19 death rates within US counties nationwide.
Related
- Spatial causal inference in the presence of unmeasured confounding and interference
- A unified framework for estimating direct causal effect under spatial confounding and interference, with the R package spaci
- Causal Inference with Unobserved Confounding: A Mixture Learning Perspective
- ProximalFM: Amortized Proximal Causal Inference under Hidden Confounding
- COSTA: Covariance-Optimized Design and Causal Inference under Network-Temporal Interference
BibTeX
@misc{paschalidis2026causal,
title = {{Causal Inference for Sequential Settings under Interference and Latent Confounding}},
author = {Phevos Paschalidis and Constantinos Daskalakis and Devavrat Shah},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2607.14940},
eprint = {2607.14940},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2607.14940},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Causal Inference for Sequential Settings under Interference and Latent Confounding
AU - Phevos Paschalidis
AU - Constantinos Daskalakis
AU - Devavrat Shah
PY - 2026
DA - 2026/11/04
PB - arXiv
DO - 10.48550/arxiv.2607.14940
UR - https://arxiv.org/abs/2607.14940
AB - We study causal inference under outcome interference for sequential, observational settings. Specifically, we consider settings where the binary outcomes over N units are Markovian across T time steps. At each time step, the outcomes of N units have dependencies captured through an Ising model; each outcome is also impacted through an external field capturing the effects of its treatment as well as latent confounders. Similar to panel data literature, these latent confounders are modeled to have a low-rank factor structure. Our data is a single sample from this high-dimensional distribution. To estimate causal quantities of interest, we provide a computationally efficient method based on Maximum Pseudo-Likelihood Estimation (MPLE) for learning the model parameters. Under mild assumptions, we establish non-asymptotic consistency for parameter estimation and show this translates to faithful estimation of causal quantities of interest after sampling from the learned model. We demonstrate the efficacy of the method through synthetic experiments as well as a real-world case-study investigating causal effects of vaccine rates on COVID-19 death rates within US counties nationwide.
ER -