nt-williams / lmtp-simulations

Code used for the simulation study in the paper "Non-parametric casual effects based on longitudinal modified treatment policies."

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

LMTP Simulations

Simulation material for "Non-parametric causal effects based on longitudinal modified treatment policies."

Authors: Ivan Díaz, Nicholas Williams, Katherine Hoffman, and Edward Schenck


Description

This repository contains the code used for the simulation study in the paper "Non-parametric casual effects based on longitudinal modified treatment policies." Simulations are designed to be run on a high performance computing cluster using Slurm. The main file structure is as follows:

  • R: Contains R function definition scripts.

  • scripts: Contains R scripts that run the simulations and summarize simulation results.

  • results: Contains simulation results.

This simulation uses a special version of the lmtp package that allows for different SuperLearner calls at every time point. This package version is available in this repository as "lmtp_1.0.0.9001.tar.gz". It can be installed using:

install.packages("lmtp_1.0.0.9001.tar.gz", repos = NULL, type = "source")

About

Code used for the simulation study in the paper "Non-parametric casual effects based on longitudinal modified treatment policies."


Languages

Language:R 98.7%Language:Shell 1.3%