Statistical methods for the analysis of ordinal response data
Statistical methods for the analysis of ordinal response data
Ordinal response models and in particular cumulative link models are the most prevalent techniques for modelling ordered response data. This thesis examines the advantages of these models versus other approaches in the socio-economic literature and assesses the performance of available residual diagnostics measures by means of simulation studies and four case studies. Furthermore, it proposes solutions to specific issues of flexible versions of cumulative link models.
University of Southampton
Lorenzo-Arribas, Altea
609bdcec-7c64-49aa-90aa-c54567962ba1
20 June 2019
Lorenzo-Arribas, Altea
609bdcec-7c64-49aa-90aa-c54567962ba1
Overstall, Antony
09be306c-8513-46dc-9321-4f3439fbc4cb
Lorenzo-Arribas, Altea
(2019)
Statistical methods for the analysis of ordinal response data.
University of Southampton, Doctoral Thesis, 217pp.
Record type:
Thesis
(Doctoral)
Abstract
Ordinal response models and in particular cumulative link models are the most prevalent techniques for modelling ordered response data. This thesis examines the advantages of these models versus other approaches in the socio-economic literature and assesses the performance of available residual diagnostics measures by means of simulation studies and four case studies. Furthermore, it proposes solutions to specific issues of flexible versions of cumulative link models.
Text
Final thesis
- Version of Record
More information
Published date: 20 June 2019
Identifiers
Local EPrints ID: 436174
URI: http://eprints.soton.ac.uk/id/eprint/436174
PURE UUID: 3774734b-3ff6-46a3-b7cc-3b2da6487831
Catalogue record
Date deposited: 02 Dec 2019 17:31
Last modified: 16 Mar 2024 04:55
Export record
Contributors
Author:
Altea Lorenzo-Arribas
Thesis advisor:
Antony Overstall
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics