Profile identification via weighted related metric scaling: an application to dependent Spanish children Articles uri icon

publication date

  • June 2015

start page

  • 593

end page

  • 618

issue

  • 3

volume

  • 178

international standard serial number (ISSN)

  • 0964-1998

electronic international standard serial number (EISSN)

  • 1467-985X

abstract

  • Disability and dependence (lack of autonomy in performing common everyday actions) affect health status and quality of life; therefore they are significant public health issues. The main purpose of this study is to use classicalmulti-dimensional scaling techniques to design dependence profiles for Spanish children between 3 and 6 years old. The data come from the Survey about Disabilities, Personal Autonomy and Dependence Situations, 2008. Two distance (or dissimilarity) functions between individuals are considered: the classical approach using Gower's similarity coefficient and weighted related metric scaling. Both approaches can cope with different types of information (quantitative, multistate categorical and binary variables). However, the Euclidean configurations that are obtained via weighted related metric scaling present a higher percentage of explained variability and higher stability.

keywords

  • activities of daily living; disability; mixed-type data; public health; related metric scaling; principal components analysis; health; distance; biplots; people; models