% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@ARTICLE{Saadati:128189,
      author       = {M. Saadati$^*$ and A. Benner$^*$},
      title        = {{S}tatistical challenges of high-dimensional methylation
                      data.},
      journal      = {Statistics in medicine},
      volume       = {33},
      number       = {30},
      issn         = {0277-6715},
      address      = {Chichester [u.a.]},
      publisher    = {Wiley},
      reportid     = {DKFZ-2017-04207},
      pages        = {5347 - 5357},
      year         = {2014},
      abstract     = {With the fast growing field of epigenetics comes the need
                      to better understand the intricacies of DNA methylation data
                      analysis. High-throughput profiling using techniques, such
                      as Illumina's BeadArray assay, enable the quantitative
                      assessment of methylation. Challenges arise from the fact
                      that resulting methylation levels (so-called beta values)
                      are proportions between 0 and 1, often from an asymmetric,
                      bimodal distribution with peaks close to 0 and 1. Therefore,
                      the majority of standard statistical approaches do not
                      apply. The logit transformation into so-called M-values is a
                      common approach to circumvent this problem and aims to allow
                      the use of common statistical methods. However, it can be
                      observed that the transformation from beta to M-values does
                      not necessarily result in an approximately homoscedastic
                      distribution. Often, bimodality, asymmetry and
                      heteroscedasticity are conserved even after transformation.
                      We give an overview and discussion of methods suggested in
                      the recent years that attempt to address the characteristics
                      of methylation data in univariate screening settings. In
                      order to identify 'differential' methylation with respect to
                      covariates of interest while adjusting for confounders, we
                      compare parametric methods, such as linear and beta
                      regression, and nonparametric methods, such as rank-based
                      regression. Our goal is to sensitise researchers to the
                      challenges and issues that arise from this type of data as
                      well as to present possible solutions.},
      cin          = {C060},
      ddc          = {610},
      cid          = {I:(DE-He78)C060-20160331},
      pnm          = {313 - Cancer risk factors and prevention (POF3-313)},
      pid          = {G:(DE-HGF)POF3-313},
      typ          = {PUB:(DE-HGF)16},
      pubmed       = {pmid:25042556},
      doi          = {10.1002/sim.6251},
      url          = {https://inrepo02.dkfz.de/record/128189},
}