Questions tagged [causal-diagram]

Graphical methods for investigating causality, the related [confounder] tag, do-calculus, interventions, and counterfactuals.

Filter by
Sorted by
Tagged with
0 votes
0 answers
21 views

Derive and validate a probability using a causal diagram

Given a causal diagram and the conditional probabilities for every adjacent node, I want to calculate a specific probability in two ways - let's call them the "simple" and "alternate&...
user avatar
  • 1
1 vote
1 answer
34 views

Can all types of probabilistic independencies be depicted via graphs?

I was going through Probabilistic Reasoning In Intelligent Systems by Judea Pearl .In chapter 3 the author tries to motivate the need for qualitative representation of independence relations, that do ...
user avatar
0 votes
1 answer
29 views

Does an unobserved mediator causes endogeneity?

Suppose I'm modeling the probability to apply for a bank loan as a function of gender. I have then the following DAG: Wikipedia lists 3 causes of endogeneity There is measurement error. Suppose I ...
user avatar
1 vote
1 answer
57 views

How to consider time from vaccination on final outbreak size

I want to evaluate the effect of vaccination on the risk of infection during outbreaks and the change in efficacy due to the time passed from vaccination. I would like to achieve a causal ...
user avatar
  • 2,343
5 votes
1 answer
201 views

Pearl, Causal Inference in Statistics Q3.5.1 (Backdoor criterion)

This is a question about backdoor criterion (as per J. Pearl) on finding causal effects. It is linked to a specific exercise in a specific book, but I hope it will be sufficiently generic and self-...
user avatar
  • 388
1 vote
1 answer
23 views

How to evaluate validity about Causal Discovery?

When I was trying to do structural learning for causal inference, I perplex for too many causal discovery algorithms(PC, FCI, GES, NOTEARS and more...) There are many structural learning algorithm for ...
user avatar
2 votes
1 answer
121 views

Causal discovery for pairwise independent joint dependent variables

Consider the standard example for variables that are pairwise independent but joint dependent. $$ (x,y,z)= \begin{cases} (0,0,0) & \text{probability 1/4} \\ (1,1,0) & \text{probability 1/4} \\ ...
user avatar
0 votes
0 answers
67 views

Cyclic Graphs and Causal Models

I am currently working through the second edition of Pearl's book Causality: Models Reasoning and Inference. As far as I can tell, Pearl's emphasis on DAGs excludes some potentially valid sets of ...
user avatar
  • 101
2 votes
1 answer
51 views

Meaning of multiple exposures in a DAG

I am working with DAGs as a way to do some causal modeling. I am using dagitty - both the website and the R package. I feel like I have a good grasp of most things related to confounding, adjustment ...
user avatar
  • 51
0 votes
0 answers
30 views

How is backdoor criterion used in practice?

Is the backdoor criterion applicable only for "learning" in a causal model (i.e. for estimating the causal effects between variables) or must it also be used when running that model, as in ...
user avatar
1 vote
0 answers
95 views

How is a difference-in-differences model represented in a causal diagram (or directed acyclic graph)?

Unlike a standard causal model with A = Treatment, X = Confounder, and Y = Outcome: a difference-in-differences (DiD) model is concerned with estimating the Average Treatment Effect on the Treated (...
user avatar
  • 4,586
1 vote
1 answer
50 views

What justifies the multiplication step in the proof of the front-door adjustment?

$\newcommand{\doop}{\operatorname{do}}$ The proofs of the front-door adjustment that I've read take three steps: Show $P(M|\doop(X))$ is identifiable Show $P(Y|\doop(M))$ is identifiable Multiply the ...
user avatar
  • 172
2 votes
1 answer
22 views

Dealing with competing events from a CI perspecrive

Suppose I am a company eager to get at the (causal) effect between age and the event of contract termination. However, people can also die instead of actively terminating a contract. This seems like a ...
user avatar
1 vote
0 answers
19 views

Parents in a directed acyclic graph vs a partial ancestral graph

In DAGs, parents are defined as follows: A is a parent of B if 'A -> B' edge is in the graph. In PAGs, there are mixed type of edges, so you can have A -> B, A o-> B. Obviously if A -> B,...
user avatar
  • 153
1 vote
0 answers
24 views

Good example of a walk-through of the FCI algorithm to ensure all steps are done

The FCI algorithm is a common algorithm used for learning a Markov equivalence class of causal graphs from observational data. I am wondering if there are any good examples that walk through a causal ...
user avatar
  • 153
4 votes
1 answer
109 views

Predictive parametric models and their (unknowable?) coefficients signs

Suppose the DAG below is the true, complete, DAG for the effect of $Exercise$ on $Cholesterol$. $Exercise$ lowers $Cholesterol$; $Age$ causes people to $Exercise$ more; $Age$ causes $Cholesterol$ to ...
user avatar
0 votes
1 answer
30 views

the causal factors in a subtracting relationship in directed acyclic graph

I have one variable A which is derived from subtracting C from B, i.e., A=B-C, does that mean B and C are both the causal factors of A if depicted in A DAG?
user avatar
  • 143
2 votes
0 answers
42 views

Algorithm to check if there is an inducing path between two nodes - constructing maximal ancestral graph (MAG) given a DAG

In causal inference, one generally learns a Markov equivalence class of causal graphs when trying to reconstruct causal structure from data. This is known as a maximal ancestral graph (MAG). I am ...
user avatar
  • 153
1 vote
1 answer
42 views

DAG: what is the type of variable that only influences exposure?

What is the type of the left variable if this is not an instrument or conditional instrument? Is it just a covariate? Moderator?
user avatar
  • 1,533
0 votes
0 answers
18 views

Is duration of treatment effect a classic mediator variable in a causal diagram?

My team is drawing up a causal diagram for a retrospective study to estimate the treatment effect (ATT) of home health nursing on patients with multiple chronic health conditions: where we have A = ...
user avatar
  • 4,586
1 vote
1 answer
39 views

DAG: how descendant, collider and mediator most likely affect the effect between exposure and outcome?

I made a very simple scenario: Let's assume 'total work time' has a positive association with 'income' (more you work, more you earn). But when I adjust to one of the following DAG's members, what ...
user avatar
  • 1,533
5 votes
1 answer
77 views

Intuition and meaning of a "discriminating path" in a causal DAG

In Ali, Richardson and Spirtes (2009) (open copy here) and many other papers in the causal DAG literature, there is the notion of a "discriminating path". The definition is: A path $\pi = ⟨...
user avatar
  • 153
0 votes
0 answers
13 views

Statistical methods for overcoming residual confounding with administrative health data

I have extensive administrative health data (general patient demographics + medical information, place of residence, many study years, few outcome measures) that have limited variables for effectively ...
user avatar
  • 1,533
1 vote
0 answers
23 views

Causal graph based on data generation process

I am quite new to causal inference and want to try some methods for treatment effect estimation. For this purpose, I created a the following data generation process in Python: ...
user avatar
  • 11
0 votes
0 answers
25 views

Doing causal inference when my causal graph has cycles and is therefore not a DAG

Let's say I have a system of variables that I reasonably believe to have a feedback loop. Let's look at this toy example outside_temperature → ...
user avatar
  • 767
1 vote
0 answers
31 views

Choice of Markov Random Field or Bayesian Network to model some causal and some non-causal links

Suppose you were modelling whether a person's ethnicity meant that they had different chances of getting a job due to discrimination. You have a couple of confounding variables e.g. deprivation - in ...
user avatar
  • 617
1 vote
1 answer
47 views

Book of Why, causal diagram 9.5 - how does that represent Kruskal's argument?

In the Book of Why, Judea Pearl, there is the case of a Berkley admission gender discrimination paradox which was solved by Peter Bickel. The solution was done by searching for discrimination ...
user avatar
2 votes
1 answer
71 views

Book Of Why, Judea Pearl - Dependence of guinea pig weights on gestation period

In the Book Of Why by Judea Pearl there is the mention of the dependence of weights of guinea pig pups on gestation period, as explored by Sewall Wright. The following is the causal diagram provided - ...
user avatar
3 votes
1 answer
35 views

Confounder choice to minimize variance in causal estimate

Let's imagine we have data generated according to the DAG X -> y <- U2 ^ ^ | | U0 -> U1 I was running some simulations (below) to work on my ...
user avatar
2 votes
1 answer
51 views

How to define Unit-specific quantity of the effect of a continuous variable on another continuous one?

Recently Lundberg, 2021 [1] emphasized the necessity to define a unit-specific quantity, target population, and causal diagram, to clarify the theoretical and empirical estimands of any quantitative ...
user avatar
2 votes
0 answers
55 views

effect of vaccination against covid on hospitalization - help building a causal DAG [closed]

During the covid crisis, we have seen explanations of why vaccinated people end up less hospitalized than unvaccinated people under the paradox that there were more vaccinated people hospitalized than ...
user avatar
  • 355
2 votes
1 answer
78 views

Causal Inference in a Bayesian Network with unobservable backdoor and no frontdoor

Just like the Bayesian network shown above. I want to identify the average treatment effect(ATE) from Smoking to Lung Cancer. If Genetics is observable, I can easily identify the ATE with Pearl's ...
user avatar
1 vote
2 answers
81 views

Doubts on a proof about graphical models

This is the third question I am asking about these notes http://www.stat.cmu.edu/~larry/=sml/DAGs.pdf .This time it is about the proof of a small theorem (page 426), that I report: Theorem: Let $G$ ...
user avatar
  • 693
0 votes
0 answers
18 views

Estimation of Treatment Effect using Bayesian Nets

I am trying to estimate a causal effect using DAGs in R. While by now I can fit baysian nets, draw DAGs, and can validate the independence conditions of my models, I still have no clue how to ...
user avatar
3 votes
1 answer
34 views

Identifiability of multivariate instrumental variable model

I'm interested in estimating the effects of $X_1$ and $X_2$ on $Y$ in the directed acyclic graph below. $U_1$ and $U_2$ are unobserved confounders. Based on Definition 7.4.1 on p. 248 of Causality ...
user avatar
  • 31
0 votes
1 answer
131 views

Adjustment set for the DAG

I have the following DAG From Dagitty tool, I am getting minimum adjustment set as Growth when the exposure is Treatment and outcome is dANB and UC is the unobserved confounder variable. If the ...
user avatar
  • 35
0 votes
1 answer
27 views

Variable type name in causal inference

Causal inference language distinguishes different variable types: confounders, mediators, colliders, moderators. Some time ago I encountered quite rare variable name which I can not remember. The idea ...
user avatar
  • 1,676
3 votes
2 answers
86 views

Determining direct cause with some "realization" of `V \ {X, Y}`

I'm bouncing around "Causality" by Judea Pearl. On page 222 it offers this definition of a direct cause: "$X$ is a direct cause of $Y$" if there exist two values $x$ and $x'$ of $...
user avatar
1 vote
1 answer
126 views

Pearl's Front-door and Back-door

I've encountered lots of causal inference terms and jargons (under the Neyman-Rubin potential outcome framework), and I had a question regarding how Pearl's DAG restrictions relate to ignorability and ...
user avatar
  • 173
0 votes
0 answers
57 views

Causal Inference: Ignorability and Collider

I've encountered lots of causal inference terms and jargons (under the Neyman-Rubin potential outcome framework), and I had questions regarding ignorability. Is it the case that ignorability is always ...
user avatar
  • 173
1 vote
1 answer
256 views

Causal Inference: Moderation and Mediation

I've encountered lots of causal inference terms and jargons (under the Neyman-Rubin potential outcome framework), and I had a question regarding mediator and moderator. Is it the case that moderation /...
user avatar
  • 173
1 vote
0 answers
114 views

Causal Inference: Selection Bias and Endogeneity [closed]

I've encountered lots of causal inference terms and jargons (under the Neyman-Rubin potential outcome framework), and I had questions regarding their relationships: I know that exogeneity E(e|X) = 0 ...
user avatar
  • 173
2 votes
1 answer
27 views

When is the knowledge of the causal mechanism useful for pure prediction?

In many settings, we are only interested in building a good predictor: e.g. $E(y_t | x_{t-1})$, where $y_t$ and $x_{t-1}$ are vectors of arbitrary dimension. However, sometimes we are also given, or ...
user avatar
  • 308
4 votes
1 answer
246 views

Causal inference - difference between blocking a backdoor path and adding a variable to regression

I have just started this introductory course to causal inference. The DAG approach is completely new to me even though I come from an econometric background (though that dates back to 15 years ago). ...
user avatar
  • 355
5 votes
1 answer
1k views

causal graph - counting the number of backdoor paths in a DAG

I am following "A Crash Course in Causality: Inferring Causal Effects from Observational Data" on Coursera. I am struggling at correctly identifying backdoor paths in causal graphs (or DAG ...
user avatar
  • 355
6 votes
1 answer
111 views

Cyclicality in causal relationships

Causal graphs are an increasingly popular tool for causal inference. The underlying understanding of causality is deterministic. In the popular directed acyclic form of causal graphs, we assume that ...
user avatar
  • 137
5 votes
1 answer
67 views

Role of regression model fit in causal analysis

When analysing causal questions, we use DAGs that give us covariates needed for modelling. But another time we assess model fit to get the best prediction. These two approaches have different purposes ...
user avatar
  • 1,533
2 votes
0 answers
41 views

Is it possible to have a set of variables as exposure in a causal DAG?

I am working on identifiablity of a test (target) distribution based on the training distribution using interventional graphs. generally, I am wondering is it possible to consider a set of variables ...
user avatar
1 vote
1 answer
29 views

How are prerequisites/eligibility criteria defined in causal contexts?

In a causal graph (DAG), $A\to B$ means $A$ causes $B.$ Even correlation can be defined with causal relationships (for example, maybe $A$ is correlated with $B$ because $C$ causes both $A$ and $B$). ...
user avatar
0 votes
1 answer
48 views

Instrumental Variable and "Exclusivity"

In the following DAG: Can I use IV1 as an instrument for exposure? In the this video at 4:26 the teacher explains a principle of "exclusivity" for instrumental variables. Cutoff causes ...
user avatar