Please use this identifier to cite or link to this item: http://hdl.handle.net/10995/101684
Title: Criteria for analysis and comparison of experimental data under conditions of uncertainty
Authors: Kumkov, S. I.
Kataeva, Z. V.
Shilovskikh, O. V.
Issue Date: 2020
Publisher: American Institute of Physics Inc.
Citation: Kumkov S. I. Criteria for analysis and comparison of experimental data under conditions of uncertainty / S. I. Kumkov, Z. V. Kataeva, O. V. Shilovskikh. — DOI 10.1063/5.0027282 // AIP Conference Proceedings. — 2020. — Vol. 2293. — 140008.
Abstract: The paper deals with investigation of the important problem of processing the ophthalmic data on the post-operation status of patients. The groups of patients differ by the type (technology) of fixing the intraocular lenses (IOL). Validity of each type of technology is estimated by computation of criteria for distinction of data between groups. The initial information comprises measurements of several ophthalmic indices. The samples on each index are very short; in each index, as a rule, the samples of patients' groups overlap each other; any probabilistic characteristics of the measuring indices are unknown; any probabilistic characteristics of the measuring errors are also unknown. So, the standard methods of mathematical statistics can be applied only in the formal way and have shown to be inefficient. In contrast, the Hausdorff distance (from the set theory) as the criterion of distinction between two samples (both for one- and, especially, for two-dimensional indices) demonstrated to be reliable to distinct the patient's status. Computations of the Hausdorff distance are valid for any relative location of point sets under comparison. © 2020 American Institute of Physics Inc.. All rights reserved.
Keywords: COMPARISON
CRITERIA
DISTINCTION
ESTIMATION
EXPERIMENTAL OPHTHALMIC DATA
GROUPS
PATIENTS
POST OPERATION PROCESSION
SAMPLES
URI: http://hdl.handle.net/10995/101684
Access: info:eu-repo/semantics/openAccess
SCOPUS ID: 85097977021
PURE ID: 20396989
60ca31d9-895a-4510-acf7-e9ac9cb1c992
ISSN: 0094243X
ISBN: 9780735440258
DOI: 10.1063/5.0027282
metadata.dc.description.sponsorship: The work was supported by the RFBR grant, project no. 18-01-00410.
Appears in Collections:Научные публикации, проиндексированные в SCOPUS и WoS CC

Files in This Item:
File Description SizeFormat 
2-s2.0-85097977021.pdf328,39 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.