Over-optimism in benchmark studies and the multiplicity of design and analysis options when interpreting their results

by   Christina Nießl, et al.

In recent years, the need for neutral benchmark studies that focus on the comparison of methods from computational sciences has been increasingly recognised by the scientific community. While general advice on the design and analysis of neutral benchmark studies can be found in recent literature, certain amounts of flexibility always exist. This includes the choice of data sets and performance measures, the handling of missing performance values and the way the performance values are aggregated over the data sets. As a consequence of this flexibility, researchers may be concerned about how their choices affect the results or, in the worst case, may be tempted to engage in questionable research practices (e.g. the selective reporting of results or the post-hoc modification of design or analysis components) to fit their expectations or hopes. To raise awareness for this issue, we use an example benchmark study to illustrate how variable benchmark results can be when all possible combinations of a range of design and analysis options are considered. We then demonstrate how the impact of each choice on the results can be assessed using multidimensional unfolding. In conclusion, based on previous literature and on our illustrative example, we claim that the multiplicity of design and analysis options combined with questionable research practices lead to biased interpretations of benchmark results and to over-optimistic conclusions. This issue should be considered by computational researchers when designing and analysing their benchmark studies and by the scientific community in general in an effort towards more reliable benchmark results.


page 1

page 2

page 3

page 4


Four principles for improved statistical ecology

Increasing attention has been drawn to the misuse of statistical methods...

Designing Laboratory Notebooks for Managing Software-based Scientific Studies

Scientific processes rely on software as an important tool for data acqu...

Pitfalls and Potentials in Simulation Studies

Comparative simulation studies are workhorse tools for benchmarking stat...

Teaching reproducible research for medical students and postgraduate pharmaceutical scientists

In many academic settings, medical students start their scientific work ...

Hazards in Deep Learning Testing: Prevalence, Impact and Recommendations

Much research on Machine Learning testing relies on empirical studies th...

AdaptMemBench: Application-Specific MemorySubsystem Benchmarking

Optimizing scientific applications to take full advan-tage of modern mem...

Consideration Set Sampling to Analyze Undecided Respondents

Researchers in psychology characterize decision-making as a process of e...

Please sign up or login with your details

Forgot password? Click here to reset