Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Vector quantization and clustering in presence of censoring

Abstract : We consider the problem of optimal vector quantization for random vectors with one censored component and applications to clustering of censored observations. We introduce the definitions of the empirical distortion and of the empirically optimal quantizer in presence of censoring and we establish the almost sure consistency of empirical design. Moreover, we provide a non asymptotic exponential bound for the difference between the performance of the empirically optimal k-quantizer and the optimal performance over the class of all k-quantizers. As a natural application of the new quantization criterion, we propose an iterative two-step algorithm allowing for clustering of multivariate observations with one censored component. This method is investigated numerically through applications to real and simulated data.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

Cited literature [31 references]  Display  Hide  Download
Contributor : Svetlana Gribkova <>
Submitted on : Sunday, October 19, 2014 - 2:30:03 PM
Last modification on : Tuesday, July 21, 2020 - 3:19:01 AM
Document(s) archivé(s) le : Friday, April 14, 2017 - 12:07:01 PM


Files produced by the author(s)


  • HAL Id : hal-01075676, version 1


Svetlana Gribkova. Vector quantization and clustering in presence of censoring. 2014. ⟨hal-01075676⟩



Record views


Files downloads