Missing data in multiple correspondence analysis under the available data principle of the NIPALS algorithm

Multiple correspondence analysis (MCA) in the presence of missing data is usually performed by removing the records that have missing or not available (NA) data; sometimes, an entire row or column of a data matrix is removed, which is not ideal because relevant information on an individual or variab...

Full description

Bibliographic Details
Main Authors:	Andrés Felipe Ochoa Muñoz, Víctor Manuel Gonzalez Rojas, Campo Elías Pardo Turriago
Format:	Article
Language:	English
Published:	Universidad Nacional de Colombia 2019-10-01
Series:	Dyna
Subjects:	multiple correspondence analysis missing data nipals available data principle
Online Access:	https://revistas.unal.edu.co/index.php/dyna/article/view/80261

id	doaj-76e9f42d91e1411983a6ad1dc0bf66ce
record_format	Article
spelling	doaj-76e9f42d91e1411983a6ad1dc0bf66ce2020-11-25T02:40:04ZengUniversidad Nacional de Colombia Dyna0012-73532346-21832019-10-018621124925710.15446/dyna.v86n211.8026152397Missing data in multiple correspondence analysis under the available data principle of the NIPALS algorithmAndrés Felipe Ochoa Muñoz0Víctor Manuel Gonzalez Rojas1Campo Elías Pardo Turriago2Universidad del ValleUniversidad del ValleUniversidad Nacional de Colombia - Sede BogotáMultiple correspondence analysis (MCA) in the presence of missing data is usually performed by removing the records that have missing or not available (NA) data; sometimes, an entire row or column of a data matrix is removed, which is not ideal because relevant information on an individual or variable of the study is lost. In some cases, it is assumed that the missing data are a category of the qualitative variable, resulting in a greater variance dispersion in the new axes. Possible solutions to this problem can be the imputation of the missing data or using an algorithm suited to the presence of this type of data. This work is focused on performing the MCA method in the presence of missing data, without using imputation techniques, by using the available data principle of the nonlinear estimation by iterative partial least squares (NIPALS) algorithm [25].https://revistas.unal.edu.co/index.php/dyna/article/view/80261multiple correspondence analysismissing datanipalsavailable data principle
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Andrés Felipe Ochoa Muñoz Víctor Manuel Gonzalez Rojas Campo Elías Pardo Turriago
spellingShingle	Andrés Felipe Ochoa Muñoz Víctor Manuel Gonzalez Rojas Campo Elías Pardo Turriago Missing data in multiple correspondence analysis under the available data principle of the NIPALS algorithm Dyna multiple correspondence analysis missing data nipals available data principle
author_facet	Andrés Felipe Ochoa Muñoz Víctor Manuel Gonzalez Rojas Campo Elías Pardo Turriago
author_sort	Andrés Felipe Ochoa Muñoz
title	Missing data in multiple correspondence analysis under the available data principle of the NIPALS algorithm
title_short	Missing data in multiple correspondence analysis under the available data principle of the NIPALS algorithm
title_full	Missing data in multiple correspondence analysis under the available data principle of the NIPALS algorithm
title_fullStr	Missing data in multiple correspondence analysis under the available data principle of the NIPALS algorithm
title_full_unstemmed	Missing data in multiple correspondence analysis under the available data principle of the NIPALS algorithm
title_sort	missing data in multiple correspondence analysis under the available data principle of the nipals algorithm
publisher	Universidad Nacional de Colombia
series	Dyna
issn	0012-7353 2346-2183
publishDate	2019-10-01
description	Multiple correspondence analysis (MCA) in the presence of missing data is usually performed by removing the records that have missing or not available (NA) data; sometimes, an entire row or column of a data matrix is removed, which is not ideal because relevant information on an individual or variable of the study is lost. In some cases, it is assumed that the missing data are a category of the qualitative variable, resulting in a greater variance dispersion in the new axes. Possible solutions to this problem can be the imputation of the missing data or using an algorithm suited to the presence of this type of data. This work is focused on performing the MCA method in the presence of missing data, without using imputation techniques, by using the available data principle of the nonlinear estimation by iterative partial least squares (NIPALS) algorithm [25].
topic	multiple correspondence analysis missing data nipals available data principle
url	https://revistas.unal.edu.co/index.php/dyna/article/view/80261
work_keys_str_mv	AT andresfelipeochoamunoz missingdatainmultiplecorrespondenceanalysisundertheavailabledataprincipleofthenipalsalgorithm AT victormanuelgonzalezrojas missingdatainmultiplecorrespondenceanalysisundertheavailabledataprincipleofthenipalsalgorithm AT campoeliaspardoturriago missingdatainmultiplecorrespondenceanalysisundertheavailabledataprincipleofthenipalsalgorithm
_version_	1724783219818102784

Missing data in multiple correspondence analysis under the available data principle of the NIPALS algorithm

Similar Items