Exceeding chance level by chance: The caveat of theoretical chance levels in brain signal classification and statistical assessment of decoding accuracy.
By Etienne Combrisson, K. Jerbi. Journal of Neuroscience Methods, 2015
607 citations recorded by the source corpus.
Subfields: Cognitive Neuroscience
View Paper: https://www.semanticscholar.org/paper/6caf3f7ca0c78d1863bf7d17656ee164f1c6f465
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Cognitive Neuroscience
- Ovidiu V. Lungu
- A. Casson
- Emma Gowen
- Ellen Poliakoff
- Andrius Vabalas
- Gernot R. Müller-Putz
- Habib Benali
- Julien Doyon
Citations in the corpus
- Learning machines and sleeping brains: Automatic sleep stage classification using decision-tree multi-class support vector machines. (2015, result): “Note here that although such theoretical chance levels are ot reliable for small sample sizes (Combrisson and Jerbi, 2015), he very high number of segments used here for each sleep stage see Table 4) and high classification percentages obtained, allows o safely assess our results by comparison to su”
- Consolidation alters motor sequence-specific distributed representations (2018, methodology): “However, the classification-based measures they used may have biased their parametric statistical results by violating both the normality assumption and theoretical null-distribution (Jamalabadi et al., 2016; Allefeld et al., 2016; Combrisson and Jerbi, 2015; Varoquaux, 2018) and may have thus been ”
- Domain Adaptation Techniques for EEG-Based Emotion Recognition: A Comparative Study on Two Public Datasets (2019, methodology): “on the classifier and the number of test samples [35], [36].”
- Machine learning algorithm validation with a limited sample size (2019, methodology): “In contrast to Combrisson and Jerbi [5] in our simulation we used not only K-fold CV but also other validation methods.”
- Neural interactions in the human frontal cortex dissociate reward and punishment learning (2024, background): “The shuffling led to a distribution of MI reachable by chance, for each contact and at each time point (Combrisson and Jerbi, 2015).”