Can Confirmation Measures Reflect Statistically Sound Dependencies in Data? The Concordance-based Assessment
The paper considers particular interestingness measures, called confirmation measures (also known as Bayesian confirmation measures), used for the evaluation of “if evidence, then hypothesis” rules. The agreement of such measures with a statistically sound (significant) dependency between the eviden...
Main Authors: | Susmaga Robert, Szczęch Izabela |
---|---|
Format: | Article |
Language: | English |
Published: |
Sciendo
2018-03-01
|
Series: | Foundations of Computing and Decision Sciences |
Subjects: | |
Online Access: | https://doi.org/10.1515/fcds-2018-0004 |
Similar Items
-
Can interestingness measures be usefully visualized?
by: Susmaga Robert, et al.
Published: (2015-06-01) -
Clustering the objective interestingness measures based on tendency of variation in statistical implications
by: Nghia Quoc Phan, et al.
Published: (2016-05-01) -
Classification of objective interestingness measures
by: Lan Phuong Phan, et al.
Published: (2016-09-01) -
Multivariate measures of concordance for
copulas and their marginals
by: Taylor M. D.
Published: (2016-10-01) -
EVALUATION AND OPTIMIZATION OF FREQUENT ASSOCIATION RULE BASED CLASSIFICATION
by: Izwan Nizal Mohd Shaharanee, et al.
Published: (2014-06-01)