https://github.com/bdwilliamson/flevr_supplementary

Supplementary materials for the `flevr` paper

https://github.com/bdwilliamson/flevr_supplementary

Science Score: 10.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
  • .zenodo.json file
  • DOI references
  • Academic publication links
    Links to: arxiv.org
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (10.6%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

Supplementary materials for the `flevr` paper

Basic Info
  • Host: GitHub
  • Owner: bdwilliamson
  • License: mit
  • Language: R
  • Default Branch: main
  • Size: 92.8 KB
Statistics
  • Stars: 0
  • Watchers: 3
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 3 years ago · Last pushed over 2 years ago
Metadata Files
Readme License

README.md

Supplementary materials for the flevr paper

This repository contains code to reproduce the analyses in "Flexible variable selection in the presence of missing data" by Williamson and Huang (International Journal of Biostatistics, 2023). All analyses were implemented in the freely available R programming language; specifically, version 4.0.2. All analyses use the R package flevr version 0.0.2.

This README file provides an overview of the code available in the repository.

Code directory

We have separated our code further into two sub-directories based on the two main objectives of the manuscript:

  1. Numerical experiments to evaluate the operating characteristics of our proposed method under varying data-generating mechanisms (sims).
  2. Developing a biomarker panel for pancreatic cancer early detection (data_analysis).

All analyses were performed on a Linux cluster using the Slurm batch scheduling system. The head node of the batch scheduler allows the shorthand "ml" in place of "module load". If you use a different batch scheduling system, the individual code files are flagged with the line where you can change batch variables. If you prefer to run the analyses locally, you may -- however, these analyses will then take a large amount of time.


Issues

If you encounter any bugs or have any specific questions about the analysis, please file an issue.

Owner

  • Name: Brian Williamson
  • Login: bdwilliamson
  • Kind: user
  • Location: Seattle, Washington USA
  • Company: Kaiser Permanente Washington Health Research Institute

Assistant Investigator at Kaiser Permanente Washington Health Research Institute. Interested in inference in high-dimensional settings.

GitHub Events

Total
Last Year