Comparing two K-category assignments by a K-category correlation coefficient

By Jan Gorodkin. 2004

532 citations recorded by the source corpus.

Subfields: Molecular Biology, Statistics and Probability, Evaluation & Benchmarks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

In Statistics and Probability

In Evaluation & Benchmarks

Citations in the corpus

GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding (2018, methodology): “Evaluation Since the class distribution in the diagnostic set is not balanced, we use R3 (Gorodkin, 2004), a three-class generalization of the Matthews correlation coefficient, for evaluation.”
Modeling aspects of the language of life through transfer-learning protein sequences (2019, methodology): “A generalized MCC using the Gorodkin measure [101] for K (=10) categories as well as accuracy (Q10), was used to evaluate localization predictions.”
The Matthews Correlation Coefficient (MCC) is More Informative Than Cohen’s Kappa and Brier Score in Binary Classification Assessment (2021, background): “Other generalizations of the phi coefﬁcient were proposed in Janson and Vegelius [22] and Gorodkin [23].”
A Comparison of MCC and CEN Error Measures in Multi-Class Prediction (2010, methodology): “A generalization to the multi-class case was deﬁned in (Gorodkin, 2004), later used also for comparing network topologies (Supper et al., 2007; Stokic et al., 2009).”
Counterfactually-Augmented SNLI Training Data Does Not Yield Better Generalization Than Unaugmented Data (2020, methodology): “For the GLUE diagnostic sets, we follow the authors and use R3 (Gorodkin, 2004) as our evaluation metric.”
Revealing Household Characteristics from Smart Meter Data (2014, methodology): “To this end, we compute the true positive rate (TPR) and false positive rate (FPR), which are defined as TPR = TP TP+FN and FPR = FP TN+FP [41].”
Metrics for Multi-Class Classification: an Overview (2020, background): “There is no fixed minimum value and it changes every time between -1 and 0 depending on the number and on the Actual distribution of the classes in the initial dataset [6].”
DeepLoc: prediction of protein subcellular localization using deep learning (2017, methodology): “The performance measurements used to assess the performance of our models were accuracy and the Gorodkin measure (Gorodkin, 2004).”