Observational

17 papers7 directions
Observational is a research venue active from 2017 to 2025 that focuses on the intersection of statistical inference and machine learning. With a corpus of 17 papers, the venue serves as a platform for exploring methodology related to causal modeling and the analysis of non-experimental data. It is characterized by its focus on bridging the gap between predictive modeling and traditional statistical inference, often addressing the theoretical and practical challenges of drawing conclusions from observational datasets. The research published at Observational frequently addresses the "two cultures" of data modeling, seeking to reconcile algorithmic prediction with causal explanation. Key topics include the application of propensity scores, sensitivity analysis for matched studies, and double machine learning approaches for combining experimental and observational studies. Several works examine the implementation of quasi-experimental designs in fields such as healthcare, including the evaluation of COVID-19 therapies and the development of stable inference methods outside of randomized controlled trials. Prolific contributors to the venue include researchers such as Alexander Volfovsky, Cynthia Rudin, and Guido Imbens. The venue facilitates a dialogue between computer science, statistics, and econometrics, emphasizing the development of robust frameworks for causal discovery. By hosting discussions on balancing score methods and modern data modeling, Observational contributes to the evolving standards for how machine learning techniques are applied to inferential tasks in complex environments.

Papers by Year

2025 2
2023 2
2021 9
2019 2
2018 1
2017 1

Top Research Directions

Research directions most represented by papers from this venue.

Causal Inference with Unobserved Confounding 2
Semiparametric Efficiency and Efficient Influence Functions 1
Integrating Mechanistic Models with Data Driven Learning 1
Stratified Subgroup Analysis for Identifying Effect Heterogeneity 1
Testing the Validity of Instrumental Variables 1
Estimating Heterogeneous Treatment Effects with Causal Machine Learning 1
The Real World Validation Gap of Synthetic Data 1

Top Authors

AuthorPapers
Cynthia Rudin2
Guido Imbens2
Harsh Parikh2
Alan Mishler1
Daniel E. Ho1
Devdatt Dubhashi1
Elizabeth Stuart1
Emily Fox1
Giles Hooker1
Jianqing Fan1
Kaizheng Wang1
Siyu Heng1
Susan Athey1

Impactful Papers

Papers from this venue that shaped research clusters.

Influential

Papers

TitleYear
A Double Machine Learning Approach for Combining Experimental and Observational Studies2025
Safe inference outside of randomized trials: Application of the stability-controlled quasi-experiment to the effects of three COVID-19 therapies2025
The Central Role of the Propensity Score in Sensitivity Analysis for Matched Observational Studies2023
What is a propensity score? Applications and extensions of balancing score methods2023
Beyond Two Cultures: Cultural Infrastructure for Data-driven Decision Support2021
Breiman's Two Cultures: A Perspective from Econometrics2021
Breiman's Two Cultures: You Don't Have to Choose Sides2021
Bridging Breiman's Brook: From Algorithmic Modeling to Statistical Learning2021
Causal Modelling: The Two Cultures2021
Comment on "Statistical Modeling: The Two Cultures" by Leo Breiman2021
Melting together prediction and inference2021
Modern Data Modeling: Cross-Fertilization of the Two Cultures2021
The "Given Data" Paradigm Undermines Both Cultures2021
An Application of Matching After Learning To Stretch (MALTS) to the ACIC 2018 Causal Inference Challenge Data2019
Estimating Treatment Effects with Causal Forests: An Application2019
Judging Statistical Criticism2018
Regression Discontinuity Designs in the Econometrics Literature2017