% 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{Stolte:301753,
      author       = {M. Stolte and N. Schreck$^*$ and A. Slynko and M.
                      Saadati$^*$ and A. Benner$^*$ and J. Rahnenführer and A.
                      Bommert},
      collaboration = {t. g. “. data”},
      title        = {{S}imulation study to evaluate when {P}lasmode simulation
                      is superior to parametric simulation in comparing
                      classification methods on high-dimensional data.},
      journal      = {PLOS ONE},
      volume       = {20},
      number       = {6},
      issn         = {1932-6203},
      address      = {San Francisco, California, US},
      publisher    = {PLOS},
      reportid     = {DKFZ-2025-01137},
      pages        = {e0322887 -},
      year         = {2025},
      abstract     = {Simulation studies, especially neutral comparison studies,
                      are crucial for evaluating and comparing statistical methods
                      as they investigate whether methods work as intended and can
                      guide an appropriate method choice. Typically, the term
                      simulation refers to parametric simulation, i.e. computer
                      experiments using pseudo-random numbers. For these, the full
                      data-generating process (DGP) and outcome-generating model
                      (OGM) are known within the simulation. However, the
                      specification of realistic DGPs might be difficult in
                      practice leading to oversimplified assumptions. The problem
                      is more severe for higher-dimensional data as the number of
                      parameters to specify typically increases with the number of
                      variables in the data. Plasmode simulation, which is a
                      combination of resampling covariates from a real-life
                      dataset from the DGP of interest together with a specified
                      OGM is often claimed to solve this problem since no explicit
                      specification of the DGP is necessary. However, this claim
                      is not well supported by empirical results. Here, parametric
                      and Plasmode simulations are compared in the context of a
                      method comparison study for binary classification methods.
                      We focus on studies conducted with some specific data type
                      or application in mind whose true, unknown data-generating
                      mechanism is mimicked. The performance of Plasmode and
                      parametric comparison studies for estimating classifier
                      performance is compared as well as their ability to
                      reproduce the true method ranking. The influence of
                      misspecifications of the DGP on the results of parametric
                      simulation and of misspecifications of the OGM on the
                      results of parametric and Plasmode simulation are
                      investigated. Moreover, different resampling strategies are
                      compared for Plasmode comparison studies. The study finds
                      that misspecifications of the DGP and OGM negatively
                      influence the ability of the comparison studies to estimate
                      the classification performances and method rankings. The
                      best choice of the resampling strategy in Plasmode
                      simulation depends on the concrete scenario.},
      keywords     = {Computer Simulation / Models, Statistical / Humans /
                      Algorithms},
      cin          = {C060},
      ddc          = {610},
      cid          = {I:(DE-He78)C060-20160331},
      pnm          = {313 - Krebsrisikofaktoren und Prävention (POF4-313)},
      pid          = {G:(DE-HGF)POF4-313},
      typ          = {PUB:(DE-HGF)16},
      pubmed       = {pmid:40455868},
      doi          = {10.1371/journal.pone.0322887},
      url          = {https://inrepo02.dkfz.de/record/301753},
}