# Tag Info

### Pearl intervention formula?

Since Pearl's intervention formula is probabilistic in nature based on graph surgery of causal graph DAGs, it's assuming true marginal and/or conditional distributions of all involved variables. And ...
• 347

### Term for two variables that are "too close for control"

The best term for such a relationship seems to be "tautological association." A definition and some examples from diverse analyses are offered by Berrie L, Arnold KF, Tomova GT, Gilthorpe ...
• 12.8k

### Sandwich variance estimator or bootstrap-based variance for stabilized inverse probability weighting (IPW)

Every estimator has a variance, and we can estimate that variance from our data. Instead of thinking about pseudo-populations and sample sizes, think about whether a procedure yields a good estimate ...
• 35k

### Sandwich variance estimator or bootstrap-based variance for stabilized inverse probability weighting (IPW)

Viewing it as multiple copies of individuals is helpful to conceptualize what IPW is doing (i.e., constructing a pseudo-population), but maybe less helpful for understanding the variance. To see why, ...
• 2,552

### Pearl intervention formula?

If in your sample data all the rows are equi-probable, then your calculations seem correct to me, except that you never compute a probability as $0/0.$ That term should just be $0.$ If an event never ...
• 5,942

### How can restricted randomization to achieve covariate balance lead to imbalance in unobserved variables?

After some thought, I have a toy example where rerandomization (to achieve balance in the observed covariate $x$) leads to imbalance in another variable $z$. Imagine we need to randomize a binary ...
• 663

### When the direction of causation can plausiblely run in either direction, is there a good stat approach to distinguishing relative strength?

If you have good timeseries data of each, the standard approach would likely be granger causality or transfer entropy. Note that these approaches are not necessarily measures of true causality, but I ...

### Experiment design to determine effect of ads on etsy shop performance

I think a simple pre-post analysis is going to be challenging. Since sales are infrequent, you would need two long periods to detect any difference. But that means you will conflate the effect of ads ...
• 37.3k

### What is the math rationale behind the inverse probability weighting?

Inverse probability of treatment weighting doesn't create pseudo-individuals so there's no need to derive their outcome. The idea of IPTW is that that you have a binary treatment variable $T$, an ...
• 41.6k
Accepted

### Causal variables and causal independence of the noise variables

Consider a system described by the behavior and interrelations of a finite set of variables $\mathcal{V}=\{V_i\}_{i=1}^m$, where each variable $V_i$ is a function/mechanism $f_i$ evaluation of some ...
• 2,278

### How can restricted randomization to achieve covariate balance lead to imbalance in unobserved variables?

You say If we balance for covariates with restricted randomization, any positively/negatively correlated unobserved variable would also become better balanced. For uncorrelated variables, they would ...
• 81.4k

### How can restricted randomization to achieve covariate balance lead to imbalance in unobserved variables?

A few things. First, my read of the passage is not that restricted randomization leads to imbalance in unobserved covariates. Rather, despite the researcher's best intentions, restricted ...
Accepted

### What are indirect and common cause links?

The phrase ... $\hat{\mathcal{P}}(X_t^j)$ are sufficient to establish conditional independence (Markov property), that is, to identify indirect and common cause links... refers to the fact that the ...
• 2,278