% 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{Piper:140670,
author = {Piper, Sophie K and Grittner, Ulrike and Rex, Andre and
Riedel, Nico and Fischer, Felix and Nadon, Robert and
Siegerink, Bob and Dirnagl, Ulrich},
title = {{E}xact replication: {F}oundation of science or game of
chance?},
journal = {PLoS biology},
volume = {17},
number = {4},
issn = {1545-7885},
address = {Lawrence, KS},
publisher = {PLoS},
reportid = {DZNE-2020-06992},
pages = {e3000188},
year = {2019},
abstract = {The need for replication of initial results has been
rediscovered only recently in many fields of research. In
preclinical biomedical research, it is common practice to
conduct exact replications with the same sample sizes as
those used in the initial experiments. Such replication
attempts, however, have lower probability of replication
than is generally appreciated. Indeed, in the common
scenario of an effect just reaching statistical
significance, the statistical power of the replication
experiment assuming the same effect size is approximately
$50\%-in$ essence, a coin toss. Accordingly, we use the
provocative analogy of 'replicating' a neuroprotective drug
animal study with a coin flip to highlight the need for
larger sample sizes in replication experiments.
Additionally, we provide detailed background for the
probability of obtaining a significant p value in a
replication experiment and discuss the variability of p
values as well as pitfalls of simple binary significance
testing in both initial preclinical experiments and
replication studies with small sample sizes. We conclude
that power analysis for determining the sample size for a
replication study is obligatory within the currently
dominant hypothesis testing framework. Moreover,
publications should include effect size point estimates and
corresponding measures of precision, e.g., confidence
intervals, to allow readers to assess the magnitude and
direction of reported effects and to potentially combine the
results of initial and replication study later through
Bayesian or meta-analytic approaches.},
keywords = {Animals / Bayes Theorem / Biomedical Research: methods /
Biomedical Research: statistics $\&$ numerical data / Data
Interpretation, Statistical / Humans / Models, Statistical /
Probability / Publications / Reproducibility of Results /
Research Design: statistics $\&$ numerical data / Sample
Size},
cin = {AG Dirnagl},
ddc = {610},
cid = {I:(DE-2719)1810002},
pnm = {344 - Clinical and Health Care Research (POF3-344)},
pid = {G:(DE-HGF)POF3-344},
typ = {PUB:(DE-HGF)16},
pubmed = {pmid:30964856},
pmc = {pmc:PMC6456162},
doi = {10.1371/journal.pbio.3000188},
url = {https://pub.dzne.de/record/140670},
}