-
Hi,
I have been given a very large cohort matched on a previously estimated propensity score (PS) and cannot feasibly re-estimate and rematch. I have the estimated PS and the matched pairs identified…
-
In the MatchIt documentation I can't find any information on how to do matching by specific covariates (e.g. age, sex). I.e. I don't want to do propensity score matching, but I want to match patients…
-
Does dowhy support multiple treatments?
I've used a toy dataframe, constructed a CausalModel with several treatment variables, identified estimands, and then ran
model.estimate_effect(identified_e…
-
I wasn't sure how to respond to Soren's comments on his push, so I thought I would respond here so that everyone can communicate in one place. Let me know if this doesn't work for people, I'm happy to…
-
https://github.com/Kanaries/Rath/blob/d2cabfef63f845df85e23b3d306f6ac455cef76e/services/causal-service/algorithms/dowhy/ExplainData.py#L219
```python
graph = constructPAG(fields, causalModel)
…
-
I was using version 4.5.2 as of 6-7 days ago and seeing the following set of results that change as expected when I change the caliper from 0.1 to 0.5.
![Screenshot (11)](https://user-images.githu…
-
Thanks for producing a great resource for R users.
I am using MatchIt for the first time, and have been surprised by the long runtime of the matching procedure, even when using a relatively small d…
-
I performed propensity score matching using the nearest neighbor method with the MatchIt-package. To assess the balance by matching I used the bal.tab function of the COBALT package setting the thresh…
-
This is more a question then a bug report. I have a full minimal working example describing my problem at StackExchange's CrossValidated: https://stats.stackexchange.com/q/584180/126967
Usually I d…
buhtz updated
2 years ago
-