Object

Title: On Computational Problems in the Analysis of Statistical Dependence for Imprecise Data

Creator:

Hryniewicz, Olgierd. Autor ; Opara, Karol. Autor

Date issued/created:

2012

Resource type:

Text

Subtitle:

Raport Badawczy = Research Report ; RB/13/2012

Publisher:

Instytut Badań Systemowych. Polska Akademia Nauk ; Systems Research Institute. Polish Academy of Sciences

Place of publishing:

Warszawa

Description:

40 pages ; 21 cm ; Bibliography p. 40

Abstract:

This paper provides a comprehensive analysis of computational problems concerning calculation of Kendall’s τ dependence (association) measure for interval data. Exact algorithms solving this task have unacceptable com­putational complexity for larger samples, therefore we concentrate on com­putational problems arising in approximate algorithms. In particular, we propose a set of heuristics solutions for finding minimal and maximal value of Kendall’s τ for interval data. Extensive simulation experiments show that some of the heuristics yield very good starting points for optimization pro­cedures based on random generation of linear extensions or evolutionary and direct-search algorithms.This paper provides a comprehensive analysis of computational problems concerning calculation of Kendall’s τ dependence (association) measure for interval data. Exact algorithms solving this task have unacceptable com­putational complexity for larger samples, therefore we concentrate on com­putational problems arising in approximate algorithms. In particular, we propose a set of heuristics solutions for finding minimal and maximal value of Kendall’s τ for interval data. Extensive simulation experiments show that some of the heuristics yield very good starting points for optimization pro­cedures based on random generation of linear extensions or evolutionary and direct-search algorithms.

Relation:

Raport Badawczy = Research Report

Detailed Resource Type:

Report

Resource Identifier:

oai:rcin.org.pl:109176

Source:

RB-2012-13

Language:

eng

Language of abstract:

eng

Rights:

Creative Commons Attribution BY 4.0 license

Terms of use:

Copyright-protected material. [CC BY 4.0] May be used within the scope specified in Creative Commons Attribution BY 4.0 license, full text available at: ; -

Digitizing institution:

Systems Research Institute of the Polish Academy of Sciences

Original in:

Library of Systems Research Institute PAS

Projects co-financed by:

Operational Program Digital Poland, 2014-2020, Measure 2.3: Digital accessibility and usefulness of public sector information; funds from the European Regional Development Fund and national co-financing from the state budget.

×

Citation

Citation style:

This page uses 'cookies'. More information