Skip to content

ARLundborg/DOPE

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Efficient adjustment for complex covariates

Reproduces the experiment from `Efficient adjustment for complex covariates: Gaining efficiency with DOPE'.

arXiv:2402.12980

Setup

Create a virtual environment

python3 -m venv .venv && source .venv/bin/activate && pip install -r requirements.txt

To run the simulation study on synthetic data:

PYTHONPATH=. python experiments/simulation_study/run_estimators.py

To run the coverage study on synthetic data:

PYTHONPATH=. python experiments/simulation_study/run_coverage.py

The plots in the main manuscript are generated by running:

PYTHONPATH=. python plot_coverage.py PYTHONPATH=. python plot_estimators.py

The NHANES datasets were loaded and cleaned using

PYTHONPATH=. python experiments/NHANES/clean_data.py

PYTHONPATH=. python experiments/NHANES/clean_data.py --impute_all

and the NHANES analysis was run with

PYTHONPATH=. python experiments/NHANES/analyze_nhanes.py --tune_hyperparameters

PYTHONPATH=. python experiments/NHANES/analyze_nhanes.py --use_imputed --tune_hyperparameters

About

Code for simulations in arXiv:2402.12980

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages