The problem of false discoveries from a metrological point of view

2013 Joint IMEKO (International Measurement Confederation) TC1-TC7-TC13 Symposium: Measurement Across Physical and Behavioural Sciences

D'Errico, Giampaolo E.^1

Istituto Nazionale di Ricerca Metrologica (INRIM), Torino, Italy^1

关键词: False discovery rate;    Hypothesis testing;    Statistical significance test;   

Others  :  https://iopscience.iop.org/article/10.1088/1742-6596/459/1/012041/pdf
DOI  :  10.1088/1742-6596/459/1/012041

来源: IOP

【 摘 要 】

Valid inference drawn from analysis of experimental results needs scientific grounds, whereas conclusions based on statistical significance tests or hypothesis testing may be problematic, especially when dealing with a multiplicity of tested hypotheses, as in experiments performed on bio-molecules. The problem of false discovery rate is focused in the present paper, aiming at eliciting application of sound criteria for rejection/acceptance of hypotheses and related methods of uncertainty characterisation.