Correspondence analysis: handling cell-wise outliers via the reconstitution algorithm
Correspondence analysis: handling cell-wise outliers via the reconstitution algorithm
Correspondence analysis (CA) is a popular technique to visualize the relationship between two categorical variables. CA uses the data from a two-way contingency table and is affected by the presence of outliers. The supplementary points method is a popular method to handle outliers. Its disadvantage is that the information from entire rows or columns is removed. However, outliers can be caused by cells only. In this paper, a reconstitution algorithm is introduced to cope with such cells. This algorithm can reduce the contribution of cells in CA instead of deleting entire rows or columns. Thus the remaining information in the row and column involved can be used in the analysis. The reconstitution algorithm is compared with two alternative methods for handling outliers, the supplementary points method and MacroPCA. It is shown that the proposed strategy works well.
MacroPCA, supplementary points, visualization, incidence matrix, outliers, contingency table
96-122
Qi, Qianqian
47673ec0-7ef7-413d-8102-10789990f40c
Hessen, David J.
5e4ddabd-0df6-48e4-8c6e-478e2f1940ec
Vonk, Aike N.
2e3cc931-9fb5-4dc3-a5c8-7237c743f9dd
Van Der Heijden, Peter
85157917-3b33-4683-81be-713f987fd612
July 2025
Qi, Qianqian
47673ec0-7ef7-413d-8102-10789990f40c
Hessen, David J.
5e4ddabd-0df6-48e4-8c6e-478e2f1940ec
Vonk, Aike N.
2e3cc931-9fb5-4dc3-a5c8-7237c743f9dd
Van Der Heijden, Peter
85157917-3b33-4683-81be-713f987fd612
Qi, Qianqian, Hessen, David J., Vonk, Aike N. and Van Der Heijden, Peter
(2025)
Correspondence analysis: handling cell-wise outliers via the reconstitution algorithm.
Bulletin of Sociological Methodology, 167 (1), , [07591063251348789].
(doi:10.1177/07591063251348789).
Abstract
Correspondence analysis (CA) is a popular technique to visualize the relationship between two categorical variables. CA uses the data from a two-way contingency table and is affected by the presence of outliers. The supplementary points method is a popular method to handle outliers. Its disadvantage is that the information from entire rows or columns is removed. However, outliers can be caused by cells only. In this paper, a reconstitution algorithm is introduced to cope with such cells. This algorithm can reduce the contribution of cells in CA instead of deleting entire rows or columns. Thus the remaining information in the row and column involved can be used in the analysis. The reconstitution algorithm is compared with two alternative methods for handling outliers, the supplementary points method and MacroPCA. It is shown that the proposed strategy works well.
Text
Correspondence analysis- handling cell-wise outliers via the reconstitution algorithm
- Author's Original
Text
qi-et-al-2025-correspondence-analysis-handling-cell-wise-outliers-via-the-reconstitution-algorithm
- Version of Record
More information
Accepted/In Press date: 26 April 2024
e-pub ahead of print date: 21 July 2025
Published date: July 2025
Keywords:
MacroPCA, supplementary points, visualization, incidence matrix, outliers, contingency table
Identifiers
Local EPrints ID: 490023
URI: http://eprints.soton.ac.uk/id/eprint/490023
ISSN: 0759-1063
PURE UUID: 8b8fbccf-b5db-405d-abe3-4354dda147ec
Catalogue record
Date deposited: 13 May 2024 17:03
Last modified: 18 Sep 2025 01:46
Export record
Altmetrics
Contributors
Author:
Qianqian Qi
Author:
David J. Hessen
Author:
Aike N. Vonk
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
