Stack Exchange Network

Stack Exchange network consists of 174 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange

Questions tagged [causality]

The relationship between cause and effect.

1
vote
0answers
11 views

Synthetic control and unobserved confounders

The synthetic control (cohort) method is a very promising approach to causal inference that has been used in a number of interesting studies. It's particularly useful in situations where data are only ...
0
votes
0answers
13 views

When should we use the segregated as opposed to the aggregated data?

In the book "Causal Inference In Statistics" by Pearl et al., there is the following problem (study question 1.2.2.) A baseball batter Tim has a better batting average than his teammate Frank. ...
0
votes
0answers
21 views

Prediction and Causation in regression

Several months ago I encountered this article To Explain or to Predict of Shamueli (2010). This article pointed out that the focus of regression can be on causation/explanation or prediction but, at ...
2
votes
2answers
62 views

How can we best explain causality for the uninitiated?

How can we best explain causality in layman's terms? There seem to be two main types of causality. One is probabilistic causation, the other is called determinism in philosophic circles or just ...
0
votes
0answers
11 views

How to motivate a POLS?

How would you justify the usage of Pooled OLS regression instead of Fixed effects? If I am calculating just correlation between two phenomena, may I get rid of these fixed effects? May I choose to ...
0
votes
1answer
13 views

What does it mean to condition on a variable B in causal models?

Given the causal model $A \rightarrow B \rightarrow C$, then $A$ and $C$ are independent conditioned on $B$. What does this mean?
0
votes
0answers
13 views

What does it mean for a variable to block a path between other two variables?

What does it mean for a variable $Z$ to "block" the path between variables $X$ and $Y$ in a causal model? What is the formal definition of a "block", and how can I intuitively understand this concept? ...
0
votes
0answers
28 views

A general question: Which causal procedure is better? [on hold]

For ordinary statistical models (on correlation), we can always think of some criterion of prediction accuracy to compare models(mean square error, AUC curve, concordance index, etc). However for ...
0
votes
0answers
14 views

How to validate the results of bayesian causal network?

There are many ways of validating predicting the results: MSE, MAE, AIC, CV, etc.. But I do not hear any validation way of causality. If the true networks not available, how to make sure the results ...
0
votes
0answers
20 views

Problem in creating causal model for delay analysis

knock-on" are defined as delays caused by previous late departures or arrivals. I am trying to create a model which can help predict the arrival delay of the next flights. But I don't know where to ...
1
vote
1answer
57 views

How to separate causality and reverse causality?

For a customer in a grocery store, the greater the number of purchases the longer the shopping path. On the other hand, the longer the shopping path the greater the number of goods to which the ...
2
votes
1answer
37 views

Why a path in a causal graph can have edges not all with the same direction?

In a fork, A <- C -> B, A and B are independent given C. We can say that A and B are d-separated or the path between them is blocked by C, given C. So ...
2
votes
2answers
45 views

Is individual causal effect identifiable when there is no unmeasured confounder?

From the first section of the causal inference book by Hernan and Robins (link:https://cdn1.sph.harvard.edu/wp-content/uploads/sites/1268/2018/12/hernanrobins_v1.10.37.pdf), I read that the individual ...
3
votes
3answers
58 views

Random variables X and Y are dependent conditioned on random variable Z

I intuitively understand the concept of "X and Y are independent conditioned on Z", but I don't get the concept of "X and Y are dependent conditioned on Z". Can you provide some examples which show ...
0
votes
0answers
17 views

Why do we care about the joint distribution of the endogenous variables of a causal model?

In general, we can calculate the joint distribution of the endogenous variables of a structural casual model (SCM) as follows $$ P(X, X_1, \dots, X_n) = \prod_i = P(X_i \mid \text{parent}(X_i)) $$ ...
2
votes
0answers
27 views

Conterfactual estimation in machine learning model

There are various techniques to build counterfactual estimations of certain variables for linear models in observational studies. Some of those are based on comparing the change in the predicted ...
0
votes
2answers
50 views

PCA to recover factors used during data generation. Why doesn't it work?

I often found that the results of a PCA or any kind of factor analysis are interpreted in a "causal" fashion. I.e. if a principal component with high variance explanation is found, this is interpreted,...
0
votes
1answer
27 views

Can I use a first difference variable as dependent variable in a panel regression even if it contains both positive and negative values?

Can I still use a first difference variable as the outcome variable to run a panel (say, diff-in-diff) regression? For example, my dependent variable is defined as $Y_{i,t} = M_{i,t} - M_{i,t-1} - P_{...
0
votes
1answer
21 views

Propensity score matching: covariate balance

I have one concern about propensity score matching's assumption. It seems that what propensity score is doing is to say that the choice of treatment depends on pre-treatment covariates. Suppose I am ...
0
votes
1answer
15 views

Pre.intervention and post.intervention should be contiguous in CausalImpact?

I am running a CausalImpact analysis on a time series and my pre.period goes from 01.01.15 to 30.03.15. I want my post period to be from 15.04.15 to 17.04.15. Is it ok if I create a time series that ...
0
votes
0answers
26 views

Hypothesis Causality Validation

I have analyzed mortgage data to define a "typical" profile for a first-time home buyer in 2017. Now that I have this information I would like to explain the trends shown in my graphs: why is the ...
0
votes
0answers
21 views

Model subgroup- and covariate-specific effects for binary outcome over time

I am currently planning an analysis, in which I try to separate the change in the level of a binary outcome into a subgroup- and a covariate-related effect. Let's say there are three kind of ...
4
votes
3answers
142 views

Is causal inference only from data possible?

Suppose we are given a dataset but not the capability of performing some AB testing. We do some regression using X as predictor and Y as response and get a model. Can we actually say something about ...
1
vote
1answer
31 views

Generate Variables from Causal Structure for Simulation with Binary/Indicators

I would like to generate a data set of variables from a specific causal structural (a stylized world) for simulation, similar to this answer, but most of the key variables are binary/indicators. ...
1
vote
0answers
25 views

Squaring a variable in Two-ways fixed effect

I am studying the effect of renewable energy on electricity prices. I am running a two-way fixed effects estimation on the model, with 23 countries from 2007-2016. $$price.kwh_{it} = \beta_1Perc.RE....
2
votes
0answers
33 views

Observational Data and Bias - A real problem

I'm hoping you all can provide some guidance. I'm working a problem with the following objectives and data set. I would like to be able to predict, for each unit, at each sampled moment, the expected ...
2
votes
1answer
64 views

How to test whether E[X]>E[Y] controlling for Z?

Question in mathematical terms. Assume an observation consists of three continuous variables $X$, $Y$ and $Z$. The sample comprises a sufficiently large number of observations. I would like to check ...
0
votes
1answer
24 views

Measuring causation

The tool I'm working on is used to process large number of documents. Recently, I've implemented small feature for this tool. The feature affects some % of all documents. After few days I received a ...
0
votes
0answers
13 views

Lagged Dependent Variables (are they in or are they out) Vilasuso (2001, Jounral of Econometrics)

I am really struggling with whether to include lagged dependent variables or not. I have read the logic (on this website) that a lagged dependent variable should include if its current value is ...
2
votes
1answer
31 views

Do I need to adjust for confounding when the confounder is not causal?

Suppose I have a model like $$y =\alpha + x_1\beta $$ and that there exists another variable, $x_2$, that is correlated with both $y$ and $x_1$. However, changing $x_1$ will cause changes in $x_2$ ...
4
votes
1answer
55 views

What does “randomly assigned conditional on some observable” mean intuitively?

From my textbook it say that "If the treatment in a quasi-experiment is "as if" randomly assigned, conditional on some observed variables w, then the treatment effect can be estimated using ...
2
votes
2answers
40 views

On which variables can we condition to observe a direct effect?

Suppose we're interested in the effect of $D$ on $Y$. Suppose that variables $D$ and $O$ are mutually dependent on a variable $C$, and that $Y$ is mutually dependent on variables $D$ and $O$. I find ...
0
votes
1answer
32 views

Difference-in-differences using two time series

I hope the group will be able to help on the following. I have the following policy-evaluation problem: stock exchange A reduced their trading costs after period X (say, after 2008), thus managing to ...
16
votes
3answers
658 views

How is causation defined mathematically?

What is the mathematical definition of a causal relationship between two random variables? Given a sample from the joint distribution of two random variables $X$ and $Y$, when would we say $X$ causes ...
0
votes
0answers
10 views

Testing for Causality in variance

I have read a couple of papers which mention causality in variance. For example Cheung and Ng (1996, Journal of Econometrics), "A causality-in-variance test ands its applications to financial markets"....
1
vote
1answer
38 views

If A causes B & A causes C, can B modify the effect of A on C?

Suppose I roll out an initiative to promote a new vaccine in a country, call this intervention A. A causes uptake of vaccines C, but it may or may not also cause backlash from community leaders ...
10
votes
1answer
579 views

Difference between rungs two and three in the Ladder of Causation

In Judea Pearl's "Book of Why" he talks about what he calls the Ladder of Causation, which is essentially a hierarchy comprised of different levels of causal reasoning. The lowest is concerned with ...
0
votes
1answer
11 views

how to estimate prognostic core for a continuous, multinomial, and binary treatment, respectively

Quoting David Hajage and Finbarr Leacy, respectively: "Introduced by Hansen in 2008, the prognostic score (PGS) has been presented as ‘the prognostic analogue of the propensity score’ (PPS). ...
1
vote
0answers
18 views

Assesing impact for rolling enrollment data

I'm running an experiment where some of the users are shown a new widget when they become eligible (some conditions that are unrelated to the experiment itself). I have a control counterfactual group ...
1
vote
1answer
29 views

In propensity score matching, what violations or implications may result from having fitted propensity scores that are not centered at 0.5?

I currently have a procedure doing propensity score matching, and I use the fitted propensity scores (obtained via a glm call) and match on those. It turns out that I have about 60-70% more fitted ...
0
votes
0answers
25 views

Structural VAR and Strctural Causal Model

Since eighties age to now the Structural VARs (SVAR) are used to quantify and test causal relations among economic variables in econometrics literature. However today seem that Pearl’s contribution on ...
0
votes
1answer
57 views

Pearl, Causality: what are variables and functional relationship?

In Pearl "Causality: Models...", he defines Causal Structure in (2.2.1) in terms of "variables" and "functional relationships". This language conflicts with standard mathematical language where a ...
0
votes
0answers
17 views

Problem with assessing bidirectional effects

My dataset has four endogenous variables, namely, employment (emp), addiction (addict), depression (...
6
votes
3answers
230 views

Regression and causality in econometrics

In regression in general and in linear regression in particular causal interpretation about parameters is sometimes permitted. At least in econometrics literature, but not only, when causal ...
73
votes
7answers
12k views

The Book of Why by Judea Pearl: Why is he bashing statistics?

I am reading The Book of Why by Judea Pearl, and it is getting under my skin1. Specifically, it appears to me that he is unconditionally bashing "classical" statistics by putting up a straw man ...
3
votes
2answers
117 views

Is Granger causality still relevant?

Staying abreast with statistics publications is no small feat, but I did put effort into scoping out what causality papers were coming out. The most recent Granger causality paper I came across was ...
0
votes
1answer
31 views

Conditional treatment effect and average treatment effect under no unmeasured confounders (ignorability)

The conditional treatment effect (CATE) is defined as: $$ \tau(x) = \mathbb{E} \left[ Y^1- Y^0 \mid X = x \right], $$ the average treatment effect (ATE) is defined as $$ \tau_{ATE} = \mathbb{E}\...
1
vote
1answer
40 views

Why can you not bypass the strong ignorability/unconfoundness assumption via iterated expectations?

Suppose we have that $\left(Y(1), Y(0)\right)$ are potential outcomes with $X$ being the covariate and $Z$ the treatment assignment. Typically in causal inference, one will assume strong ignorability ...
1
vote
0answers
25 views

What does “structural” mean in marginal structural models and structural nested models?

Robins developed the marginal structural models and the structural nested models. An example of the structural nested models is $$E[Y^a-Y^{a=0}\mid A=a, L]=\beta_1a + \beta_2aL,$$ where $Y^a$ is the ...
2
votes
1answer
144 views

non stochastic regressors

In the multiple linear regression analysis if regressors are non-stochastic the causal interpretation of parameters is automatically permitted? I think so, because it seems me that the model can be ...