Live briefing
Everything about Ignorability
Statistical concept
In statistics, ignorability is a feature of an experiment design whereby the method of data collection does not depend on the missing data. A missing data mechanism such as a treatment assignment or survey sampling strategy is "ignorable" if the missing data matrix, which indicates which variables are observed or missing, is independent of the missing data conditional on the observed data. It has also been called unconfoundedness, selection on the observables, or no omitted variable bias. Wikipedia →
🧭 Start here: a 6-step reading path
- Read the overview: IgnorabilityA 5-minute orientation
- Skim a recent paper: Multiply Robust Estimation of Causal Effects under Principal IgnorabilityInfluential work since 2022
- Pick up a classic book: Tobacco RoadThe most-reprinted book on the subject
- Read the landmark paper: Efficient semiparametric estimation of multi-valued treatment effects under ignorabilityCited 520 times
- Go sideways: Propensity score matchingA closely related topic
- Go sideways: Rubin causal modelA closely related topic
📖 Definitions
Noun The quality of being ignorable.
🗂️ The subject at a glance
No outline available.
🏆 Landmark papers (most cited)
Efficient semiparametric estimation of multi-valued treatment effects under ignorability
Ignorability and Coarse Data
Ignorability and Coarse Data: Some Biomedical Examples
VIOLATING IGNORABILITY OF TREATMENT BY CONTROLLING FOR TOO MANY FACTORS
Limitations of individual causal models, causal graphs, and ignorability assumptions, as illustrated by random confounding and design unfaithfulness
Ignorability in general incomplete-data models
Partial and latent ignorability in missing-data problems
Ignorability and stability assumptions in neighborhood effects research
🆕 Influential since 2022
Multiply Robust Estimation of Causal Effects under Principal Ignorability
Sensitivity analyses for the principal ignorability assumption using multiple imputation
In Nonparametric and High-Dimensional Models, Bayesian Ignorability is an Informative Prior
Republican freedom, domination, and ignorability
Off-policy evaluation in partially observed Markov decision processes under sequential ignorability
📚 Books worth reading
Tobacco RoadErskine Caldwell · 1932
FactfulnessHans Rosling, Ola Rosling · 2018- 📕Perspectives on Ignorance from Moral and Social PhilosophyRik Peels, Martijn Blaauw · 2016
UnknowersLinsey McGoey · 2019
Democracy and Political IgnoranceIlya Somin · 2013- 📕Ignorance and ChangeAdriana Mica, Anna Horolets · 2020
Understanding IgnoranceDaniel R. DeNicola · 2017
Perils of PerceptionBobby Duffy · 2018
Ranked by number of editions on Open Library, a rough measure of how lasting a book is.
🔗 Related topics
- Propensity score matching In the statistical analysis of observational data, propensity score matching (PSM) is a statistical matching technique that attempts to estimate the effect…
- Rubin causal model The Rubin causal model (RCM), also known as the Neyman–Rubin causal model, is an approach to the statistical analysis of cause and effect based on the…
- Causal model In metaphysics and statistics, a causal model (also called a structural causal model) is a conceptual model that represents the causal mechanisms of a…
- Do-calculus Do-calculus is a set of mathematical rules devised by Judea Pearl in 1995 to determine whether causal effects can be identified from observational data…
- Average treatment effect The average treatment effect (ATE) is a measure used to compare treatments (or interventions) in randomized experiments, evaluation of policy interventions…
- Local average treatment effect In econometrics and related empirical fields, the local average treatment effect (LATE), also known as the complier average causal effect (CACE), is the…
- Targeted maximum likelihood estimation Targeted Maximum Likelihood Estimation (TMLE) (also more accurately referred to as Targeted Minimum Loss-Based Estimation) is a general statistical estimation…
- Inverse probability weighting Inverse probability weighting is a statistical technique for estimating quantities related to a population other than the one from which the data was collected…