Multi-Source Causal Inference Using Control Variates under Outcome Selection Bias.

We apply this framework to inference from observational data under outcome selection bias, assuming access to an auxiliary small dataset from which we can obtain a consistent estimate of the ATE. ... For example, many large observational datasets (e.g., case-control studies in epidemiology, click-through data in recommender systems) suffer from selection bias on the outcome, which makes the average ... Acknowledgements This work was supported in part by the Mathematical Data Science program of the Office of Naval Research under grant number N00014-18-1-2764. ...

arXiv:2103.16689v2 fatcat:5ixxaomfrnehpcuzuwxx5k24ay

Multiple Versions

Because of population heterogeneity, causal inference with observational data in social science may suffer from two possible sources of bias: (1) bias in unobserved pretreatment factors affecting the outcome ... Even when we control for observed covariates, these two biases may occur if the classic ignorability assumption is untrue. ... In this section, I will consider why population heterogeneity may lead to biases in causal inference. Let us assume that a population, U, is being studied. ...

doi:10.3233/iks-2012-0197 pmid:23970824 pmcid:PMC3747843 fatcat:fahsw663premthzbrgfivqbl4q

Treatment effect estimation, a fundamental problem in causal inference, has been extensively studied in statistics for decades. ... task, i.e., treatment, covariates, and outcome. ... For example, Causal Effect Variational Autoencoder (CEVAE) [Louizos et al., 2017] is based on Variational Autoencoders (VAE), which follows the causal structure of inference with proxies. ...

arXiv:2302.00848v1 fatcat:il4witxo5vgujirkgwn7gcrwhe

Sources of error and weaknesses in study design that may aVect estimates of ecological eVects include: a lack of variation in the ecological exposure (and health outcome) in the available data; not allowing ... for intraclass correlation; selection bias; confounding at both the ecological and individual level; misclassification of variables; misclassification of units of analysis and assignment of individuals ... The framework is organised under six subheadings: ensuring variation of the ecological exposure; precision and multi-level statistical methods; selection bias; confounding; information bias; model specification ...

doi:10.1136/jech.54.5.367 pmid:10814658 pmcid:PMC1731678 fatcat:vanzushxevfxxlexmyk4o4fy74

The paper introduced the psychological findings on causal learning in human cognition, then it introduced the traditional statistical solutions on causal discovery and causal inference. ... The paper reviewed recent deep causal learning algorithms with a focus on their architectures and the benefits of using deep nets and discussed the gap between deep causal learning and the needs of robotic ... These algorithms are designed to address the selection bias between the treated groups and the control groups. Both samples and covariate re-weighting are used to address the selection bias. ...

arXiv:2212.12597v1 fatcat:dbcxo7r7arhkdcktmiwhpinv24

Open Access

We use a case study to demonstrate the framework and its potential to strengthen causal inference in multi-cohort studies through improved analysis design and clarity in the interpretation of findings. ... The 'target trial' is a powerful tool for guiding causal inference in single-cohort studies. ... Specifically, there are three key causal biases that are important to consider: confounding bias, selection bias, and measurement bias. ...

arXiv:2206.11117v4 fatcat:sbnjltbvtfh2tfhn2nrdbvqhnm

Open Access Multiple Versions

This is especially true in studies involving causal inference, for which semantic and substantive differences inhibit interdisciplinary dialogue and collaboration. ... In this paper, we group nonrandomized study designs into two categories: those that use confounder-control (such as regression adjustment or propensity score matching) and those that rely on an instrument ... Box 3 Types of Bias and Assumptions for Causal Inference 1. Confounding or omitted variable bias or bias from selection into treatment: The key bias introduced by lack of randomization. ...

doi:10.1016/j.ssmph.2019.100526 pmid:31890846 pmcid:PMC6926350 fatcat:3i6zxq5ujzhfhiwt5kbaqpbpd4

DOAJ

Due to population heterogeneity, causal inference with observational data in social science is impossible without strong assumptions. There are two potential sources of bias. ... Of particular interest is the way in which composition bias, a form of selection bias, arises even under the classic assumption of ignorability, as I demonstrate with a simple simulation example. ... Economists have resorted to using unobservable variables to represent the two sources of selection bias that remain after the control of propensity score. ...

doi:10.1073/pnas.1303102110 pmid:23530202 pmcid:PMC3631652 fatcat:whgzutfbqrfdxcobtoyz6sakqi

Szczepanski

In this survey, we provide a comprehensive review of causal inference methods under the potential outcome framework, one of the well known causal inference framework. ... Moreover, the commonly used benchmark datasets as well as the open-source codes are also summarized, which facilitate researchers and practitioners to explore, evaluate and apply the causal inference methods ... Besides, a biased subset of the treated group is required to be removed to simulate the selection bias. ...

arXiv:2002.02770v1 fatcat:kcedeyseevb3doht4pop26rqvy

Controlling these factors as substitute confounders, under mild assumptions, can eliminate the bias incurred by multi-cause confounders. ... Observing that confounders in recommendations are usually shared among items and are therefore multi-cause confounders, we model the recommendation as a multi-cause multi-outcome (MCMO) inference problem ... To eliminate confounding bias, classical causal inference techniques demand us to find, measure and control all confounders C ui and calculate E[R ui (A ui )] from E C ui [E [R ui (A ui ) | C ui , A u ...

arXiv:2201.02088v2 fatcat:tykfyd4ozzhh5m4qlo656vqaxi

Open Access Multiple Versions

Given the continous advancements in deep learning methodologies, there has been a notable surge in its utilization for the estimation of causal effects using counterfactual data. ... effect estimation to industry; 3) we also endeavor to present a detailed categorization and analysis on relevant datasets, source codes and experiments. ... Traditional recommender systems extract user preference based on learning correlation in data observational, resulting in biases including selection bias, exposure bias, position bias, conformity bias, ...

arXiv:2209.08860v6 fatcat:uqw2ugrgsfbl3cr7am22v366gq

Multiple Versions

Uncritical and exclusive use of indicators of study quality such as publication status, reporting quality, and single summative quality scores are rejected. ... In this work, investigators aim to develop plausible, causal inferences about an intervention's effects. ... Were results reported selectively or for all outcomes measured? There are several ways to use these guidelines (Higgins & Green, 2006) . ...

doi:10.1177/1049731508317278 fatcat:xp2z6bknjrfbbb42if546hdmuu

confounders, selection bias and estimation bias. ... While many deep learning-based causal discovery and causal inference methods have been proposed, there is a lack of reviews exploring the internal mechanism of deep learning to improve causal learning. ... This work is supported by the Ministry of Science and Technology of China under Grant No. 2020AAA0108401，and the Natural Science Foundation of China under Grant Nos. 72225011 and 71621002. ...

arXiv:2211.03374v1 fatcat:x7dzzkrijneufpsdpmvitsbhhe

Randomized Controlled Trials (RCTs) are pivotal in generating internally valid estimates with minimal assumptions, serving as a cornerstone for researchers dedicated to advancing causal inference methods ... for researchers working on refining and applying causal inference methods. ... Validity of Identifying Assumptions under Covariate Shifts One primary source of bias when aiming to estimate externally valid causal effects arises from differences in the underlying distribution of treatment ...

arXiv:2402.17042v2 fatcat:ripvsgusmnfarbaok3z4idzlny

Open Access Multiple Versions

The former reflects the analyst's ability to draw valid inferences about the relevant causal relationship under study, whereas the latter reflects the extent to which valid inferences (based on a given ... Causal inference is a central goal of social science. ... CASe SeleCtion, CAuSAl infeRenCe, And thReAtS to inteRnAl VAlidity There is perhaps no better place to begin an examination of the conditions under which case selection may threaten the internal validity ...

doi:10.1093/jopart/mus051 fatcat:evyuyhqcdzchdickqhvsegtl4u

Multi-Source Causal Inference Using Control Variates [article]

Preserved Fulltext

CAUSAL INFERENCE AND HETEROGENEITY BIAS IN SOCIAL SCIENCE

Preserved Fulltext

Causal Effect Estimation: Recent Advances, Challenges, and Opportunities [article]

Preserved Fulltext

Ecological effects in multi-level studies

Preserved Fulltext

Deep Causal Learning for Robotic Intelligence [article]

Preserved Fulltext

Causal inference in multi-cohort studies using the target trial framework to identify and minimize sources of bias [article]

Preserved Fulltext

Other Versions

Alternative causal inference methods in population health research: Evaluating tradeoffs and triangulating evidence

Preserved Fulltext

Population heterogeneity and causal inference

Preserved Fulltext

A Survey on Causal Inference [article]

Preserved Fulltext

Deep Causal Reasoning for Recommendations [article]

Preserved Fulltext

Other Versions

A Survey of Deep Causal Models and Their Industrial Applications [article]

Preserved Fulltext

Other Versions

Study Quality Assessment in Systematic Reviews of Research on Intervention Effects

Preserved Fulltext

Deep Causal Learning: Representation, Discovery and Inference [article]

Preserved Fulltext

Towards Generalizing Inferences from Trials to Target Populations [article]

Preserved Fulltext

Case Selection in Public Management Research: Problems and Solutions

Preserved Fulltext