@inproceedings{fdi:010073292,
  title = {{D}etecting low-complexity confounders from data},
  author = {{R}uiz {C}uevas, {M}.{V}. and {S}okolovska, {N}. and {W}uillemin, {P}.{H}. and {Z}ucker, {J}ean-{D}aniel},
  editor = {},
  language = {{ENG}},
  abstract = {{S}tatistical dependencies between two variables {X} and {Y} indicate that either {X} causes {Y} , or {Y} causes {X}, or there exists a latent variable {Z} which influences {X} and {Y}. {I}n biology and medicine, an important problem is to find genetic or environmental unobserved causes of phenotypic difference between individuals. {I}n this contribution, we introduce a novel approach to identify unobserved confounders in data. {T}he proposed method is based on the state-of-the-art 3off2 causal network reconstruction algorithm, and on an evidence for a direct causal relation represented by purity of con-ditionals. {T}he proposed method is implemented in {P}ython, and it will be publicly available shortly. {W}e discuss the results obtained on a real biomedical dataset.},
  keywords = {{INTELLIGENCE} {ARTIFICIELLE} ; {INFORMATIQUE} {SCIENTIFIQUE} ; {ANALYSE} {MULTIVARIABLE} ; {MEDECINE} ; {BIOLOGIE}},
  numero = {80},
  pages = {3},
  booktitle = {},
  year = {2018},
  URL = {https://www.documentation.ird.fr/hor/fdi:010073292},
}