@inproceedings{91b10424900e43ababe37535432e81f9,

title = "Ranking Accuracy for Logistic-GEE Models",

abstract = "The logistic generalized estimating equations (logistic-gee) models have been extensively used for analyzing clustered binary data. However, assessing the goodness-of-fit and predictability of these models is problematic due to the fact that no likelihood is available and the observations can be correlated within a cluster. In this paper we propose a new measure for estimating the generalization performance of the logistic gee models, namely ranking accuracy for models based on clustered data (ramcd). We define ramcd as the probability that a randomly selected positive observation is ranked higher than randomly selected negative observation from another cluster. We propose a computationally efficient algorithm for ramcd. The algorithm can be applied for two cases: (1) when we estimate ramcd as a goodness-of-fit criterion and (2) when we estimate ramcd as a predictability criterion. This is experimentally shown on clustered data from a simulation study and a biomarkers{\textquoteright} study.",

author = "Nasser Davarzani and Ralf Peeters and Evgueni Smirnov and Jo{\"e}l Karel and {Brunner-la Rocca}, Hans-peter",

year = "2016",

month = sep,

day = "21",

doi = "10.1007/978-3-319-46349-0_2",

language = "English",

isbn = "978-3-319-46348-3",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "14--25",

editor = "H Bostr{\"o}m and A Knobbe and C Soares and P Papapetrou",

booktitle = "IDA 2016: Advances in Intelligent Data Analysis XV",

address = "United States",

}