Tau de Kendall

Résumé

En statistique, le tau de Kendall (ou \tau de Kendall) est une statistique qui mesure l'association entre deux variables. Plus spécifiquement, le tau de Kendall mesure la corrélation de rang entre deux variables. Elle est nommée ainsi en hommage à Maurice Kendall qui en a développé l'idée dans un article de 1938 bien que Gustav Fechner ait proposé une idée similaire appliquée aux séries temporelles dès 1897. Définition Soit (x_1,y_1), (x_2,y_2), \dots, (x_n,y_n) un ensemble d'observations des variables jointes X et Y tel que les valeurs des (x_i) et (y_i) sont uniques. Les paires d'observations (x_i,y_i) et (x_j,y_j) sont dites concordantes si x_iy_j. Elles sont dites discordantes si x_iy_j ou si x_i>x_j et y_i

Source officielle

https://fr.wikipedia.org/wiki/Tau_de_Kendall

À propos de ce résultat

Cette page est générée automatiquement et peut contenir des informations qui ne sont pas correctes, complètes, à jour ou pertinentes par rapport à votre recherche. Il en va de même pour toutes les autres pages de ce site. Veillez à vérifier les informations auprès des sources officielles de l'EPFL.

Publications associées (5)

Publications associées

Chargement

Personnes associées

Chargement

Unités associées

Chargement

Concepts associés (4)

Concepts associés

Chargement

Cours associés (3)

Cours associés

Chargement

Séances de cours associées (3)

Séances de cours associées

Chargement

LinvPy : a Python package for linear inverse problems

Guillaume François Paul Beaud

The goal of this project is to make a Python package including the tau-estimator algorithm to solve linear inverse problems. The package must be distributed, well documented, easy to use and easy to extend for future developers.

2016

Chargement

SEKV-E: Parameter Extractor of Simplified EKV I-V Model for Low-Power Analog Circuits

Christian Enz, Hung-Chi Han

This paper presents the open-source Python-based parameter extractor (SEKV-E) for the simplified EKV (sEKV) model, which enables the modern low-power circuit designs with the inversion coefficient design methodology. The tool extracts the essential sEKV parameters automatically from the given I-V curves using the direct extraction and the multi-stage optimization process. It also handles the overfitting issue because of non-linear least squares. Moreover, this work demonstrates the SEKV-E as a universal tool by widely applying it to different silicon technologies, temperatures, dimensions, and back-gate voltages.

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2022

Chargement

Evaluating the Explainers: Black-Box Explainable Machine Learning for Student Success Prediction in MOOCs

Natasa Krco, Mirko Marras, Vinitra Swamy

Neural networks are ubiquitous in applied machine learning for education. Their pervasive success in predictive performance comes alongside a severe weakness, the lack of explainability of their decisions, especially relevant in human-centric fields. We implement five state-of-the-art methodologies for explaining black-box machine learning models (LIME, PermutationSHAP, KernelSHAP, DiCE, CEM) and examine the strengths of each approach on the downstream task of student performance prediction for five massive open online courses. Our experiments demonstrate that the families of explainers do not agree with each other on feature importance for the same Bidirectional LSTM models with the same representative set of students. We use Principal Component Analysis, Jensen-Shannon distance, and Spearman's rank-order correlation to quantitatively cross-examine explanations across methods and courses. Furthermore, we validate explainer performance across curriculum-based prerequisite relationships. Our results come to the concerning conclusion that the choice of explainer is an important decision and is in fact paramount to the interpretation of the predictive results, even more so than the course the model is trained on. Source code and models are released at http://github.com/epfl-ml4ed/evaluating-explainers.

2022

Chargement