causal-inference-in-R
causal-inference-in-R copied to clipboard
malcolmbarrett
Causal Inference in R: A book!
The touring plans data may not meet the need for censored time-to-event data. Might have an alternate option in this pet adoption data: [https://www.kaggle.com/c/sliced-s01e10-playoffs-2/data](https://www.kaggle.com/c/sliced-s01e10-playoffs-2/data) H/T Max Kuhn: [https://topepo.github.io/2021-r-pharma/index.html#3](https://topepo.github.io/2021-r-pharma/index.html#3)
I think I have a working simulation that shows the contrast in non-collapsibility effects in models that were generated with additive and multiplicative models. @LucyMcGowan, what do you think? One...
Maybe a box in the DAG chapter saying something like: >In its purest form, a DAG represents the full causal structure for variables of interest. That is, if only one...
- [ ] Determine section to discuss #234 - [ ] Update sections that mention it to match findings and recommendations
Missing data
Lucy's slides https://onlinelibrary.wiley.com/doi/full/10.1002/sim.8355: > Results indicated that the Within approach produced unbiased estimates with appropriate confidence intervals, whereas the Across approach produced biased results and unrealistic confidence intervals
- [ ] https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5008911/
Ideas: * Move sensitivity to after outcome model, then cover specialty sensitivity analyses in the relevant chapters * Collapse the two exposure chapters, then g-comp, then doubly robust without ML...