Questions tagged [causality]
The relationship between cause and effect.
1,969 questions
1 vote
0 answers
25 views
When testing a specific hypothesis regarding HTE with "best_linear_projection" in a Causal Forest, is it valid to halve the p-value?
I’m using the "grf" package in R and its "best_linear_projection" function, which regresses doubly robust (AIPW) scores on a set of covariates/features. I have a directional ...
- 11
2 votes
1 answer
37 views
Inverse probability treatment weighting for causal inference and relevant population
When we use inverse probability of treatment weighting for causal inference, my understanding is that the generated estimate is no longer applicable to the sample\population\dataset you started with. ...
0 votes
0 answers
33 views
Regression Discontinuity with longitudinal data and possibility of multiple treatments
I'm wondering how to approach this project idea: I found that the Department of Housing and Urban Development (HUD) requires that areas it allocates funding towards have a population of at least 50,...
- 21
2 votes
0 answers
29 views
Recovering causal effects from a selection bias mechanism and the positivity assumption under internal and external consistency
I have a question regarding the recoverability from selection bias, the positivity assumption, and the internal-external consistency. Q1) In Theorem 1 of the paper "Recovering Causal Effects from ...
1 vote
0 answers
34 views
Estimating and interpreting causal effect of a continuous exposure variable on binary outcome using double machine learning
I'm using double machine learning in the structural causal modeling (SCM) framework to evaluate the effect of diet on dispersal in birds. I'm adjusting for confounding variables using the backdoor ...
- 33
6 votes
1 answer
114 views
What is the meaning of $(I - A^{\intercal})^{-1}$ in the linear Structural Equation Model (SEM) formulation of the DAG-GNN paper?
In the DAG-GNN paper (Yu et al., NeurIPS 2019, paper link), the authors describe the linear Structural Equation Model (SEM) as follows: $$X = A^{\intercal}X + Z,$$ where $A$ (an $m \times m$ matrix) ...
- 61
16 votes
3 answers
872 views
Why include unadjusted estimates in a study when reporting adjusted estimates?
Upon reading "The Strengthening the Reporting of Observational Studies in Epidemiology " or STROBE guidelines, one will find advice to (a) Give unadjusted estimates and, if applicable, ...
- 42.3k
1 vote
0 answers
47 views
Double Machine Learning: Regression Equation
I've read that Double Machine Learning (DML) uses two ML models and a regression equation. The core idea is to Predict propensity of treatment exposure given covariates, let's call this the Selection ...
- 3,970
5 votes
1 answer
353 views
Potential Outcomes as random variables rather than a fixed quantity
I am reading though Causal inference for statistics, social, and biomedical sciences : an introduction by Guido W. Imbens, Donald B. Rubin and have some confusion around treating potential outcomes as ...
- 1,106
6 votes
2 answers
301 views
Question on simple causal modeling
My causal graph looks like this: $A\to B$, $B \to C$ and $A \to C$. I want to model the direct influence of $B$ on $C$, i.e. changing $B$ by one unit, how much does $C$ change? I think the correct ...
- 509
0 votes
0 answers
31 views
Is an explicit "treatment" variable a necessary condition for instrumental variable analysis?
I'm trying to model the causal impact of our marketing efforts on our ads business, and I'm considering an Instrumental Variable (IV) framework. I'd appreciate a sanity check on my approach and any ...
- 65
0 votes
0 answers
57 views
Conceptual questions around marketing mix modeling (MMM) in the presence of omitted variables and missing not at random (MNAR) data
I need your help. Imagine a company is currently evaluating a vendor-provided MMM (Marketing Mix Modeling) solution that can be further calibrated (not used for MMM modeling validation) using ...
- 31
0 votes
0 answers
48 views
Sampling counterfactual posterior to mitigate error autocorrelation in event studies
I have question regarding event studies (pre-event data is observed, an event occurs at $t=e$, then following the treatment is assumed to be in-effect.) There are multiple approaches to event study ...
- 3,970
2 votes
0 answers
90 views
Variance of the average treatment effect using the unit-level variances of the potential outcomes
I'm reading Chapter 19 of Imbens and Rubin (2015), which is on the estimation of variance for estimators of treatment effects. They discuss using the variance of each sample/unit's potential outcomes ...
- 105
10 votes
3 answers
650 views
Why is median treatment effect not estimable?
The recent paper Addanki and Bhandari (2024) claims the median treatment effect (MTE) cannot be estimated for treatment and control groups in an observational study. The authors illustrate with an ...
- 6,644