% 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:290234,
      author       = {M. Stolte and N. Schreck$^*$ and A. Slynko and M.
                      Saadati$^*$ and A. Benner$^*$ and J. Rahnenführer and A.
                      Bommert},
      title        = {{S}imulation study to evaluate when {P}lasmode simulation
                      is superior to parametric simulation in estimating the mean
                      squared error of the least squares estimator in linear
                      regression.},
      journal      = {PLOS ONE},
      volume       = {19},
      number       = {5},
      issn         = {1932-6203},
      address      = {San Francisco, California, US},
      publisher    = {PLOS},
      reportid     = {DKFZ-2024-01050},
      pages        = {e0299989 -},
      year         = {2024},
      abstract     = {Simulation is a crucial tool for the evaluation and
                      comparison of statistical methods. How to design fair and
                      neutral simulation studies is therefore of great interest
                      for both researchers developing new methods and
                      practitioners confronted with the choice of the most
                      suitable method. The term simulation usually refers to
                      parametric simulation, that is, computer experiments using
                      artificial data made up of pseudo-random numbers. Plasmode
                      simulation, that is, computer experiments using the
                      combination of resampling feature data from a real-life
                      dataset and generating the target variable with a known
                      user-selected outcome-generating model, is an alternative
                      that is often claimed to produce more realistic data. We
                      compare parametric and Plasmode simulation for the example
                      of estimating the mean squared error (MSE) of the least
                      squares estimator (LSE) in linear regression. If the true
                      underlying data-generating process (DGP) and the
                      outcome-generating model (OGM) were known, parametric
                      simulation would obviously be the best choice in terms of
                      estimating the MSE well. However, in reality, both are
                      usually unknown, so researchers have to make assumptions: in
                      Plasmode simulation studies for the OGM, in parametric
                      simulation for both DGP and OGM. Most likely, these
                      assumptions do not exactly reflect the truth. Here, we aim
                      to find out how assumptions deviating from the true DGP and
                      the true OGM affect the performance of parametric and
                      Plasmode simulations in the context of MSE estimation for
                      the LSE and in which situations which simulation type is
                      preferable. Our results suggest that the preferable
                      simulation method depends on many factors, including the
                      number of features, and on how and to what extent the
                      assumptions of a parametric simulation differ from the true
                      DGP. Also, the resampling strategy used for Plasmode
                      influences the results. In particular, subsampling with a
                      small sampling proportion can be recommended.},
      keywords     = {Computer Simulation / Least-Squares Analysis / Linear
                      Models / Humans},
      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:38748677},
      doi          = {10.1371/journal.pone.0299989},
      url          = {https://inrepo02.dkfz.de/record/290234},
}