@article{fdi:010080443,
  title = {{M}ixed logistic regression in genome-wide association studies},
  author = {{M}ilet, {J}acqueline and {C}ourtin, {D}avid and {G}arcia, {A}ndr{\'e} and {P}erdry, {H}.},
  editor = {},
  language = {{ENG}},
  abstract = {{B}ackground{M}ixed linear models ({MLM}) have been widely used to account for population structure in case-control genome-wide association studies, the status being analyzed as a quantitative phenotype. {C}hen et al. proved in 2016 that this method is inappropriate in some situations and proposed {GMMAT}, a score test for the mixed logistic regression ({MLR}). {H}owever, this test does not produces an estimation of the variants' effects. {W}e propose two computationally efficient methods to estimate the variants' effects. {T}heir properties and those of other methods ({MLM}, logistic regression) are evaluated using both simulated and real genomic data from a recent {GWAS} in two geographically close population in {W}est {A}frica.{R}esults{W}e show that, when the disease prevalence differs between population strata, {MLM} is inappropriate to analyze binary traits. {MLR} performs the best in all circumstances. {T}he variants' effects are well evaluated by our methods, with a moderate bias when the effect sizes are large. {A}dditionally, we propose a stratified {QQ}-plot, enhancing the diagnosis of p values inflation or deflation when population strata are not clearly identified in the sample.{C}onclusion{T}he two proposed methods are implemented in the {R} package milor{GWAS} available on the {CRAN}. {B}oth methods scale up to at least 10,000 individuals. {T}he same computational strategies could be applied to other models (e.g. mixed {C}ox model for survival analysis).},
  keywords = {{GWAS} ; {M}ixed-models ; {L}ogistic regression ; {AFRIQUE} {DE} {L}'{OUEST}},
  booktitle = {},
  journal = {{BMC} {B}ioinformatics},
  volume = {21},
  numero = {1},
  pages = {536 [17 p.]},
  ISSN = {1471-2105},
  year = {2020},
  URL = {https://www.documentation.ird.fr/hor/fdi:010080443},
}