Data

Tools

Indexes

Applications

Experiments

Open Source Science

tges

Made for thesis at UCPH

https://github.com/tobiaselar/tges

Science Score: 44.0%

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

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (5.0%) to scientific vocabulary
Last synced: 7 months ago · JSON representation ·

Repository

Made for thesis at UCPH

Basic Info
  • Host: GitHub
  • Owner: tobiaselar
  • Language: R
  • Default Branch: main
  • Size: 15.2 MB
Statistics
  • Stars: 1
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created almost 2 years ago · Last pushed about 1 year ago
Metadata Files
Readme Citation

README.md

TGES

Made for thesis at UCPH

Abstract: Causal discovery with tiered background knowledge leads to more informative estimations of the true underlying data-generating DAG. In this thesis, we develop two score-based causal discovery algorithms that incorporate tiered background knowledge: Temporal Greedy Equivalence Search (TGES) and Simple Temporal Greedy Equivalence Search (Simple TGES). To be able to define the algorithms, we introduce needed graph theory, relevant score criteria, tiered background knowledge, and Greedy Equivalence Search (GES). We prove that TGES will always estimate a tiered MPDAG and that Simple TGES is sound and complete in the limit of large sample size. The algorithms have been implemented in R. We perform a simulation study, here amongst using a new metric on the performance of causal discovery algorithms. The simulation study shows that TGES outperforms Simple TGES and GES with respect to both adjacencies and orientations of edges. The computational time of TGES is slower than GES but shows potential to become faster. We finish the thesis by discussing the findings and methods used throughout.

Owner

  • Login: tobiaselar
  • Kind: user

Citation (CITATION.cff) 

# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!

cff-version: 1.2.0
title: TGES
message: >-
  If you use this software, please cite it using the
  metadata from this file.
type: software
authors:
  - given-names: Tobias Ellegaard
    family-names: Larsen
    email: tobias.e.larsen@gmail.com
    affiliation: University of Copenhagen
repository-code: 'https://github.com/tobiaselar/TGES'
abstract: >-
  This is the code used for implementing Temporal Greedy
  Equivalence Search (TGES) in R. Created for a thesis at
  UCPH.
version: 1.0.0
date-released: '2024-04-19'

GitHub Events

Total
  • Watch event: 1
  • Push event: 2
Last Year
  • Watch event: 1
  • Push event: 2