Replicability Within One Study: Harnessing Multiplicity for Observational Causal Inference

This paper addresses causal inference and modeling over event streams where data have high throughput, are unbounded, and may arrive out of order. The availability of large amount of data with these characteristics presents several new challenges related to causal modeling, such as the need for fast causal inference operations while ensuring consistent and valid results. There is no existing work specifically for such a streaming environment. We meet the challenges by introducing a time-centric causal inference strategy which leverages temporal precedence information to decrease the number of conditional independence tests required to establish the causalities between variables in a causal network. (Dependency and temporal precedence of cause over effect are the two properties of a causal relationship.) Moreover, we employ change-driven causal network inference to safely reduce the running time further. In this paper we present the Order-Aware Temporal Network Inference algorithm to model the temporal precedence relationships into a temporal network and then propose the Enhanced Fast Causal Network Inference algorithm for learning a causal network faster using the temporal network. Experiments using synthetic and real datasets demonstrate the efficacy of the proposed algorithms.

Previous chapter Next chapter Full AccessProceedings Proceedings of the 2022 SIAM International Conference on Data Mining (SDM)Learning Infomax and Domain-Independent Representations for Causal Effect Inference with Real-World DataZhixuan Chu, Stephen L. Rathbun, and Sheng LiZhixuan Chu, Stephen L. Rathbun, and Sheng Lipp.433 - 441Chapter DOI:https://doi.org/10.1137/1.9781611977172.49PDFBibTexSections ToolsAdd to favoritesExport CitationTrack CitationsEmail SectionsAboutAbstract The foremost challenge to causal inference with real-world data is to handle the imbalance in the covariates with respect to different treatment options, caused by treatment selection bias. To address this issue, recent literature has explored domain-invariant representation learning based on different domain divergence metrics (e.g., Wasserstein distance, maximum mean discrepancy, position-dependent metric, and domain overlap). In this paper, we reveal the weaknesses of these strategies, i.e., they lead to the loss of predictive information when enforcing the domain invariance; and the treatment effect estimation performance is unstable, which heavily relies on the characteristics of the domain distributions and the choice of domain divergence metrics. Motivated by information theory, we propose to learn the Infomax and Domain-Independent Representations to solve the above puzzles. Our method utilizes the mutual information between the global feature representations and individual feature representations, and the mutual information between feature representations and treatment assignment predictions, in order to maximally capture the common predictive information for both treatment and control groups. Moreover, our method filters out the influence of instrumental and irrelevant variables, and thus it effectively increases the predictive ability of potential outcomes. Experimental results on both the synthetic and real-world datasets show that our method achieves state-of-the-art performance on causal effect inference. Moreover, our method exhibits reliable prediction performances when facing data with different characteristics of data distributions, complicated variable types, and severe covariate imbalance. Previous chapter Next chapter RelatedDetails Published:2022eISBN:978-1-61197-717-2 https://doi.org/10.1137/1.9781611977172Book Series Name:ProceedingsBook Code:PRDT22Book Pages:1-737Key words:causal inference, selection bias, mutual information, real-world data

We present an instructional approach to teaching causal inference using Bayesian networks and do-Calculus, which requires less prerequisite knowledge of statistics than existing approaches and can be consistently implemented in beginner to advanced levels courses. Moreover, this approach aims to address the central question in causal inference with an emphasis on probabilistic reasoning and causal assumption. It also reveals the relevance and distinction between causal and statistical inference. Using a freeware tool, we demonstrate our approach with five examples that instructors can use to introduce students at different levels to the conception of causality, motivate them to learn more concepts for causal inference, and demonstrate practical applications of causal inference. We also provide detailed suggestions on using the five examples in the classroom.

The Target Trial: A Powerful Device Beyond Well-defined Interventions.

Justifying operational decisions for robots is a challenging task as the operator or the robot itself has to understand the underlying physical interaction between the robot and the environment to predict the potential outcome. It is desirable to understand how the decision influences the operational performance in the way of causal relationship for the purpose of explainable decision-making. Here we propose a novel causal inference framework for the discovery and inference on the reasoning of the operational decisions for robots. It unifies both domain knowledge integration and model-free causal inference, allowing a data-driven causal knowledge learning on time series data. The framework is evaluated in the experiments of an underwater robot with complex environmental interactions. The results show that the framework can learn the causal structure and inference model to accurately explain and predict the operation performance with integrated physics.

Psychologists have long had interest in the processes through which antecedent variables produce their effects on the outcomes of ultimate interest (e.g., Wood-worth's Stimulus-Organism-Response model). Models involving such meditational processes have characterized many of the important psychological theories of the 20th century and continue to the present day. However, it was not until Judd and Kenny (1981) and Baron and Kenny (1986) combined ideas from experimental design and structural equation modeling that statistical methods for directly testing such models, now known as mediation analysis, began to be developed. Methodologists have improved these statistical methods, developing new, more efficient estimators for mediated effects. They have also extended mediation analysis to multilevel data structures, models involving multiple mediators, models in which interactions occur, and an array of noncontinuous outcome measures (see MacKinnon, 2008). This work nicely maps on to key questions of applied researchers and has led to an outpouring of research testing meditational models (As of August, 2011, Baron and Kenny's article has had over 24,000 citations according to Google Scholar).

A good deal of humility: Cochran on observational studies

Based on benchmarking various methods and analyzing multiple real scRNA-seq datasets, a computational platform/workflow and a set of tips for best practices are developed for analyzing causal interactions or relationships in single cells.

Ecology has yet to embrace causal inference, yet most questions in ecology are causal. Despite the common use of terms that imply causation, such as "shapes", "drives", or "impacts", many studies shy away from directly acknowledging their causal ambitions. This avoidance not only obscures the true intent of research but also underpins a broader challenge within the field's approach to science. Ecology relies heavily on observational data, and so the necessity for robust causal inference becomes paramount. However, causal methods are also needed for non-randomised experiments. We critique the predominance in ecology of scientifically empty statistical procedures that lack scientific clarity and value. We advocate for a shift towards explicit causal inference, arguing that understanding causality is not confined to randomised controlled trials but can also be enriched through observational data when paired with rigorous causal inference methodologies. This paper elucidates the common pitfalls in ecological studies, such as throwing all variables into an analysis, use of the Akaike information criterion (AIC) for model selection, the "Table 2 fallacy" and the misuse of controls: all of which can lead to misleading scientific understanding. The good news is that causal inference is not primarily a statistical problem, but rather a scientific one that is accessible to all ecologists. We can achieve reasonable progress by continuing to use the standard statistical toolbox based around regression models, familiar to many ecologists, paired with causal diagrams. For regression, causal inference is about understanding what we should condition on (good controls) and what we should not condition on (bad controls). We provide not only a critique but a constructive guide, aiming to demystify causal inference and encourage its adoption in ecological studies using familiar approaches. By doing so, we seek to elevate the quality and impact of ecological research, moving beyond routine convenient statistical procedures and towards a more scientifically sound and insightful understanding of ecology.

Abstract: This manuscript develops a research architecture for understanding AI infrastructure at scale through the linked problems of cloud systems, GPU computing, and benchmark-driven optimization. It argues that infrastructure should be studied not as a narrow engineering substrate but as a layered socio-technical system whose performance depends on uncertainty modeling, statistical explanation, predictive learning, reproducible data lifecycles, and governance design. Across five chapters, the book moves from conceptual foundations and research design to causal and econometric inference, machine-learning based prediction and trustworthy control, scalable analytics pipelines and MLOps, and finally to applied sectoral and policy horizons. The analysis treats benchmarks as epistemic instruments that encode assumptions about relevance, risk, and legitimacy, rather than as neutral scoreboards. It further proposes that meaningful optimization requires multi-criteria evaluation across throughput, latency, energy, carbon sensitivity, resilience, and auditability. The manuscript is oriented toward publisher-ready academic use and yields concrete research outputs, including benchmark specifications, causal evidence protocols, lifecycle controls, GPU allocation frameworks, climate-aware siting templates, and governance artifacts for secure and accountable deployment. Its comparative lens emphasizes applicability across South Asia, Europe, Africa, and the Americas, showing how local institutional conditions shape the value of common methods. The result is a coherent framework for researchers, practitioners, and policymakers seeking to evaluate and govern AI infrastructure under conditions of scale, heterogeneity, and strategic importance. Keywords AI infrastructure, cloud systems, GPU computing, benchmark-driven optimization, workload forecasting, causal inference, queueing models, reinforcement learning, MLOps, telemetry pipelines, data-centre governance, edge intelligence, thermal scheduling, reproducibility, sovereign compute, post-quantum security

Description How is my immune system? Answering this question is challenging because current methods assess only isolated components rather than providing a holistic view. This project introduces an innovative blood test for evaluating the immune system comprehensively through causal omics inference. Our approach utilizes whole-blood transcriptomics data primarily from public databases such as the Gene Expression Omnibus. To generate new data, we collect blood samples using PAXgene Blood RNA Tubes, extract RNA using the PAXgene Blood RNA Kit, deplete globin mRNAs with the GLOBINclear-Human Kit, and sequence the RNA on a NovaSeq X Plus platform, achieving 50 million paired-end reads of 150 base pairs. Alternatively, and preferably, we can use the Omics One transcriptomics platform. To interpret this data, we develop a causal model represented as a network of nodes that correspond to immunologically relevant elements, including cell types and proteins. By integrating omics data into this network, we perform causal inferences to refine node probabilities and compress the network into interpretable factors. These factors are synthesized into an Immunogram, which summarizes an individual’s immune status. We present Immunograms for various conditions, including autoimmune diseases, infections, and cancers, highlighting variations in immune responses to treatments. This innovative approach enhances our understanding of individual immune profiles and supports personalized therapeutic strategies. Funding Sources Kwat Medetgul-Ernar was supported by Stanford University Medical Scientist Training Program grant T32-GM007365. Topic Categories Computational and Systems Immunology (COMP)

Causality, Reason and Causal Inference

Statistics is sometimes described as the science of reasoning under uncertainty. Statistical models provide one view of this uncertainty, but what is frequently neglected is the “invisible” portion of uncertainty: that assumed not to exist once a model has been fitted to some data. Systematic errors, i.e. bias, in data relative to some model and inferential goal can seriously undermine research conclusions, and qualitative and quantitative techniques have been created across several disciplines to quantify and generally appraise such potential biases. Perhaps best known are so-called “risk of bias” assessment instruments used to investigate the likely quality of randomised controlled trials in medical research. However, the logic of assessing the risks caused by various types of systematic error to statistical arguments applies far more widely. This logic applies even when statistical adjustment strategies for potential biases are used, as these frequently make assumptions (e.g. data “missing at random”) that can rarely be empirically guaranteed. Mounting concern about such situations can be seen in the increasing calls for greater consideration of biases caused by nonprobability sampling in descriptive inference (e.g. in survey sampling), and the statistical generalisability of in-sample causal effect estimates in causal inference. Both of these relate to the consideration of model-based and wider uncertainty when presenting research conclusions from models. Given that model-based adjustments are never perfect, we argue that qualitative risk of bias reporting frameworks for both descriptive and causal inferential arguments should be further developed and made mandatory by journals and funders. It is only through clear statements of the limits to statistical arguments that consumers of research can fully judge their value for any given application.

The previous chapter dealt with challenges that one confronts in collecting and using evidence for the generation of causal inferences. The challenges and means to address them pertain to case studies that build hypothesis, test them, or seek to modify them in order to make sense of puzzling cases. A separate and important topic reserved for this chapter concerns frequentist and Bayesian causal inference as two ways of producing inferences in tests of cross-case and within-case hypotheses. Frequentist causal inference is based on the number of observations and the premise that the more supportive or disconfirming observations one collects, the stronger causal inferences are. Bayesianism emphasizes the theoretical impact and likelihood of collecting individual observations as opposed to their number. Among other things, a discussion of these two modes of causal inferences closes the circle with respect to Chapter 3. As is detailed below, distribution-based case selection is integral to frequentist causal inference, whereas Bayesianismrelies on the theory-based choice of cases.KeywordsCausal InferenceLabor UnionConditional LikelihoodDecisive TestHigh CertaintyThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

A key challenge in the analysis of microbiome data is the integration of multi-omic datasets and the discovery of interactions between microbial taxa, their expressed genes, and the metabolites they consume and/or produce. In an effort to improve the state-of-the-art in inferring biologically meaningful multi-omic interactions, we sought to address some of the most fundamental issues in causal inference from longitudinal multi-omics microbiome data sets. We developed METALICA, a suite of tools and techniques that can infer interactions between microbiome entities. METALICA introduces novel unrolling and de-confounding techniques used to uncover multi-omic entities that are believed to act as confounders for some of the relationships that may be inferred using standard causal inferencing tools. The results lend support to predictions about biological models and processes by which microbial taxa interact with each other in a microbiome. The unrolling process helps to identify putative intermediaries (genes and/or metabolites) to explain the interactions between microbes; the de-confounding process identifies putative common causes that may lead to spurious relationships to be inferred. METALICA was applied to the networks inferred by existing causal discovery and network inference algorithms applied to a multi-omics data set resulting from a longitudinal study of IBD microbiomes. The most significant unrollings and de-confoundings were manually validated using the existing literature and databases.