Causal inference tries to quantify the effect of a change in $X$ on $Y$ whilst holding constant or eliminating all other relevant factors which might influence this relationship.

learn more… | top users | synonyms

5
votes
2answers
204 views

Does adjusting for superfluous variables bias OLS estimates?

The usual textbook treatment of adjusting for superfluous variables in OLS states that the estimator is still unbiased, but may have larger variance (see, for example, Greene, Econometric Analysis, ...
1
vote
0answers
22 views

How to program automated shrinkage for a subset of terms in R?

I've got data from a randomized experiment that includes a lot of covariates. I'm interested $\delta$ from a model of the form $y = g(\delta T + X'\beta+ \epsilon)$, where $T$ is randomly assigned and ...
0
votes
0answers
27 views

Confusion about features selection for inference analysis with lm/glm

I need a bit of tutoring about grasping the true meaning of linear regression analysis. I'd like some help in understanding well the relationships between predictors and and the meaning of adding and ...
2
votes
1answer
37 views

Propensity Score Analysis with continuous treatment

I have an observational dataset of about two dozen observed variables (continuous or discrete), plus a continuous variable of which I would like to measure the causal impact of on my dependent ...
1
vote
0answers
6 views

Adjusting for a mediator to capture cross sectional relationship

We are fitting a linear model using cross-sectional data to inspect the relationship between some exposure and an outcome (disease status, measured continuously). Duration of disease was also captured ...
1
vote
0answers
31 views

Meta-analysis: Talking about power and inference (to power)

I need a little help or reassurance concerning how to explain power "to power", i.e. to decision makers that are not well versed in statistics. The problem is this: I have done three empirical ...
1
vote
0answers
14 views

Detecting parameter influence

I have a data set consisting of a system's responses to various test configurations. Every test configuration corresponds to a different parameter set. These parameters can have either continuous ...
1
vote
0answers
47 views

Identifying What Causes a Variable to Increase

Say I have a dataset with several continuous and categorical variables, and I want to identify what variables (values or properties of these variables) may cause one of the continuous variables to ...
1
vote
0answers
27 views

How can we combine learnings from multiple experiments in a single causal model?

I would like to use a causal network modelling to model the interaction of several variables and the effects of interventions. I have measurements for all priors of the model, that is without any ...
1
vote
0answers
29 views

Do you need causal models when doing counterfactual predictions?

I am modeling the impact the number of a certain type of company (bottom of pyramid (BOP) companies, ie. companies that cater to the poorest consumers) have on market price. I considered the ...
0
votes
0answers
25 views

Is this mediation or a simple path?

This is my model adapted from a study. I want to know whether I can only study it as a path analysis without studying mediation effect (1 $\longrightarrow$ 5 direct effect, as well as indirect ...
1
vote
0answers
26 views

Inference from a sometimes-random time-series

Let's say we have two cointegrated time-series, $Y_{1}$ and $Y_{2}$, and I want to assess the causal impact of $Y_{1}$ on $Y_{2}$. There is good reason to think that both variables are influenced by a ...
0
votes
0answers
8 views

Choice of dependent variable: Differencing or Controlling?

I was running some analysis where I suspect that a treatment $D$, has opposite effects on two variables $Y^A$ and $Y^B$. To show that, I was thinking about two strategies: 1. Differencing Running ...
0
votes
0answers
12 views

Dropped cases from matched studies

We have cohort data and a rare exposure which we are matching to controls in a large epidemiologic dataset. The matching variable is a deidentified neighborhood indicator (cluster) which guarantees ...
11
votes
3answers
316 views

Real examples of Correlation confused with Causation

I'm looking for specific, real cases in which a causal relationship was inappropriately inferred from evidence of a correlation. Specifically, I'm interested in examples that meet the following ...
3
votes
3answers
101 views

Endogeneity & IV = model misspecification?

I'd like to raise a controversial point: if you need instrumental variables, your model is wrong. Basic endogeneity problem and the IV solution Let us suppose the basic framework of endogeneity and ...
0
votes
2answers
42 views

Difference between Research Design and Experimental Design

What is the difference between Research Design and Experimental Design? I can't see any difference. Both of them need to establish Causality. Both of them are the arrangement for collection and ...
5
votes
1answer
136 views

Computing inverse probability weights — conditional (multivariate) density estimation?

The general version: I need to estimate $f(A | X)$ where $A$ and $X$ are continuous and multivariate. I'd rather do it nonparametrically because I don't have a good functional form in mind and ...
2
votes
0answers
29 views

Average of percentages / prove causal relationship between sale dates & margin sales

I just wanted to make sure I'm right here. I have a situation where I need to prove that on days where we sell more than 10 items, our margin (sale price vs. suggested price) goes up. I'm not really ...
3
votes
2answers
74 views

Graphical and Statistical Tests for Robustness of Sharp RD

I'm doing sharp regression discontinuity design with my treatment variable $$ D_i = \begin{cases} 1 \enspace \quad \text{if $x_i \geq \overline{x}$} \\ 0 \quad \text{otherwise} \end{cases} $$ where ...
0
votes
1answer
32 views

Proving that the variance observed in time series A is due to the variance observed in time series B

I'm testing the hypothesis that the the variance observed in the number of medical consultations felt from 2009 through 2013 is due to the variance in user fees price, and not due to something else. ...
4
votes
1answer
43 views

Measurment error for two variables

I am interested in estimating the effect of security S on crime C in a given city over time (eight quarters) for twenty cities, so it's panel data. The problem is, instead of actual security spending ...
3
votes
0answers
19 views

Ranking of causal models

I remember seeing a paper that ranked causal statistical models, published by some research body, by quality in terms of generalizability or some similar facet(s). This would be a "hierarchy of ...
7
votes
2answers
331 views

Causality in microeconometrics versus granger causality in time-series econometrics

I understand the causality as used in microeconomics (in particular IV or regression discontinuity design) and also the Granger causality as used in time-series econometrics. How do I relate one with ...
1
vote
1answer
48 views

“Explaining” a time series - conceptual explanation needed

Imagine I have a time series for an animal population and a time series for a climatic variable during the same time period and at the same location. Unfortunately the data are observational (i.e., no ...
0
votes
1answer
57 views

Correlation and regression [duplicate]

Can there be negative correlation but the regression line has a positive change when there is an increase in the independent variable?
6
votes
1answer
168 views

How do instrumental variables address selection bias?

I'm wondering how an instrumental variable addresses selection bias in regression. Here's the example I'm chewing on: In Mostly Harmless Econometrics, the authors discuss an IV regression relating ...
1
vote
0answers
58 views

Examples for teaching: Sometimes we CAN infer causality.

There have been threads here before which posted links of the media attributing causality to correlational studies, and links to those studies have been posted. It seems as if we are always focusing ...
3
votes
1answer
95 views

Infer causality with high collinearity

I recently started to ask myself how to measure the impact of education on indexes like GDP: what is the outcome of mathematics or computer science on GDP, at the country level for instance. In this ...
2
votes
0answers
32 views

Under what circumstances is regression discontinuity preferred to differences in differences?

I am looking at the adoption of universal health care coverage for children age 6 and under in a country. The take-up rate was practically 100%. I want to know the impact of having coverage on ...
1
vote
0answers
32 views

Estimating the probability of causation based on finding a correlation, including experimental details

Say there is a hypothesis that A causes B (A -> B), and some likelihood that the hypothesis is correct (AB1%). Now, an experiment is run that claims to find a correlation between A and B. What I ...
4
votes
2answers
794 views

Difference-in-Differences Estimator for Logistic Regressions

I have a pre-post intervention study with four groups: 1) Pre-Intervention Control, 2) Pre-Intervention Treatment, 3) Post-Intervention Control, and 4) Post-Intervention Treatment. The outcome is a ...
3
votes
0answers
56 views

Estimating a confidence interval around the average of an interacted treatment effect

I've got a causal inference situation with heterogeneous treatment effects. In addition to simply estimating coefficients, I'd like to get an average effect of the treatment at the covariate values ...
1
vote
0answers
58 views

causal inference with correlated multivariate outcomes

I've been struggling with how to think about the causal estimate of a program on two outcomes, when one of the two outcomes affects the other outcome. It seems sort of like simultaneous equations, ...
2
votes
0answers
39 views

Guessing test question answers from scores

My teacher likes to give online quizzes that are about 20-30 questions long. Every student has the same questions in the same order. We are not told after taking the quiz which questions we got wrong, ...
0
votes
0answers
33 views

Causal Analysis

I want to do "Nutritional Causal Analysis". Basically my objective is to identify possible factors associated with acute malnutrition in children under five years of age in developing countries. What ...
3
votes
1answer
53 views

Average causal effect of one year increase in schooling vs a four-year increase in schooling

I'm not sure why in Mostly Harmless Econometrics, last paragraph of p. 55, the expectations of $f_{i}(s-4)$ is taken and the expectation of $f_{i}(s-1)$ is not. The text reads: Conditional on ...
2
votes
3answers
101 views

How to rule out double causation

I have a model where I suspect (purely on theoretical grounds) that double causation might be an issue. How can I test this hypothesis? I.e. I have something like $Y_i = \beta_0 + \beta_1 X_i + ...
2
votes
1answer
70 views

Why is the conditional mean of the reduced form error zero?

For example, we have a simultaneous equation model of supply and demand: Supply: $$s(p)=\alpha_{s}+\beta_{s}p+\epsilon_{s}$$ Demand: $$d(p)=\alpha_{d}-\beta_{d}p+\epsilon_{d}$$ Market clearing ...
5
votes
1answer
93 views

Is there a branch of statistics that tries to explain “why” the dataset has certain statistical properties?

Suppose I have a big dataset and I compute some statistical summary of it - e.g., the correlation of one dimension with another. I think a reasonable question to ask would be "what data points ...
1
vote
1answer
42 views

How to refer to variables which lie beyond causal pathway

Causal diagrams are extremely good tools for discussing research plans for multivariate modeling between statisticians and non-statisticians. It's easy after some deliberation to decide which ...
2
votes
1answer
124 views

Omitted Variable Bias, verification in Gretl

I am trying to verify the expression for Omitted Variable Bias (OVB) as given e.g. in Wooldridge: $\tilde{\beta_1} = \hat{\beta_1} + \hat{\beta_2} \cdot \tilde{\delta_1}$, where $\tilde{\delta_1}$ is ...
0
votes
2answers
107 views

Correlation or t-test?

Following experimental design was done and some data as shown in table below was obtained: pretest> intervention1> intervention2> posttest > perception survey Number of students=60 Number of ...
9
votes
4answers
158 views

Do edges in directed acyclic graph represent causality?

I am studying Probabilistic Graphical Models, a book for self-study. Do edges in a directed acyclic graph (DAG) represent causal relations? What if I want to construct a Bayesian network, but I am ...
5
votes
1answer
133 views

Graphical models for correlation of random variables and prediction of hidden observations

I am studying about Graphical Models and I came up with a simple example but I am not sure which kind of technique (HMM, DGM, MRF) would be able to help me with that. Imagine we have three balls that ...
2
votes
2answers
108 views

Does randomization really allow us to make claims of causality?

Lets say two groups are compared. Subjects are randomly assigned to each group, then a treatment is given to half while a placebo is given to the other half. All aspects of the experiment (order of ...
0
votes
1answer
105 views

Two highly correlated variables where both correlate with a third: Correlation and Causation

My question is certainly quite basic for statisticians! Let's suppose Var1 and Var2 are highly correlated with a poor $R^2$. ...
2
votes
1answer
65 views

Interpretation of lasso recovery results

When people say that lasso regression can under certain assumptions recover "the support", i.e. non-zero regression weights, what does this mean? This cannot mean causal recovery, because Pearl has ...
6
votes
2answers
376 views

Understanding d-separation theory in causal Bayesian networks

I am trying to understand the d-Separation logic in Causal Bayesian Networks. I know how the algorithm works, but I don't exactly understand why the "flow of information" works as stated in the ...
2
votes
0answers
96 views

Causality in Time Series

I am reading an article which is trying to justify the need for causal inference in their inferential framework. The thought experiment is as follows: Suppose a statistician is asked to design a ...