Charles Tapley Hoyt
Charles Tapley Hoyt
@srtaheri @djinnome yesterday during the discussion about the LVM with do Calculus we realized that the paper wasn't actually implementing/applying the plug-in estimator using Stan, but rather was generating a...
``` # def test_taheri(self): # """Test that all graphs produced by Sara's design algorithm can be run with :func:`identify`.""" # VIRAL_PATHOGENESIS_PATH = '../../src/y0/resources/viral_pathogenesis.json' # DEFAULT_TAG = 'type' # graph =...
1. Get examples out of [A Crash Course in Good and Bad Controls](https://ftp.cs.ucla.edu/pub/stat_ser/r493.pdf) (@vartikatewari) 2. Add a few d-separation criteria (@djinnome) 3. Try adding the rest (@vartikatewari) 4. 3-way hackathon...
Ananke already can generate semi-parametric estimators for nearly any estimand that comes out of the ID algorithm (see [here](https://ananke.readthedocs.io/en/latest/notebooks/estimation.html)). Bareinboim claims his team has developed their own estimator algorithms but...
In addition to the Robin Evans set of simplification algorithms for latent variable DAGs, we can do a couple things: 1. If there are two latent variables U1 and U2...
Future question: how many different classes of models can we get? Some combinations collapse down to the same do-calculus equation. which variables can always be excluded?
1. Given a two different probability expressions `P(...)` and `P(...)` and a (topological) ordering over all of the variables inside, what is the algorithm for ordering the two probability expressions?...
> Carette (2004) provides a formal definition for simplification in the context of Computer Algebra Systems (CAS) that operate on algebraic expressions. Modern CAS systems such as Mathematica (Wolfram Research...
See page 4 of https://causalai.net/r60.pdf We have already implemented the counterfactual (L3) language, but it might be nice to write L1 and L2 expressions as well. Further, any associational (L1)...
It would be great if the OBO export could be updated- currently the file is empty