Erroneous causal diagram in PLIV Documentation

[DARHWOLF]

Description of the issue or change proposal

https://docs.doubleml.org/stable/guide/models.html#partially-linear-iv-regression-model-pliv

There seems to be an accidental bidirected edge between the exposure variable and outcome variable in this causal diagram here for section 3.1.4. Partially linear IV regression model (PLIV)

Is this correct?

Comments, context or references

No response

[PhilippBach]

Dear @DARHWOLF ,

thanks for opening the issue. The causal graph is just one example for instrumental variables. I just paste a screenshot of the figure caption in the JSTATSOFT paper

I think the causal diagram should be alright, but please let me know if you see any issue. I agree maybe it's not the typical DAG (it's actually not Directed anymore) for IV, as for example presented in the gallery example

[DARHWOLF]

I see. Thanks for the reply. I think I missed out on the figure caption. It makes sense now. Please feel free to close this issue.

P.S. Nice work on the package!