Click here to download

Taxometric method: a statistical tool for the study of a construct’s latent structure
Author/s: Andrea Epifani 
Year:  2011 Issue: Language: Italian 
Pages:  15 Pg. 7-21 FullText PDF:  465 KB
DOI:  10.3280/RIP2011-001001
(DOI is like a bar code for intellectual property: to have more infomation:  clicca qui   and here 

The issue about the constructs’ latent structure is central in clinical psychology and psychiatry. Often, these disciplines adopt arbitrarily created diagnostic labels that are considered, a priori, as indicative of real categorical differences among subjects. The DSM-IV-TR is an example of this trend. However, the latent structure of the constructs should be empirically examined through statistical tools that are capable of evaluating whether a sample, assessed for a target construct, shows quantitative (continuous) or qualitative (categorical) differences among subjects. In the former, the sample has an unique, dimensional latent class; while in the latter, it has at least two latent class, one called taxonic and the other called complement. Taxometric method represents one of the most reliable techniques for assessing the latent structure. It includes a number of procedures relying on the analysis of the relation among a set of indicators of the construct, by examining their mathematical behavior. The inspection of the taxometric curves allows to draw inferences about the categorical vs dimensional latent structure. Taxometric method has been well validated and widely used in the last years, serving as a powerful and reliable methodology for the study of the latent structure.
Keywords: Latent structure, taxometric analysis, classification, DSM.

Andrea Epifani, Taxometric method: a statistical tool for the study of a construct’s latent structure in "RICERCHE DI PSICOLOGIA " 1/2011, pp. 7-21, DOI:10.3280/RIP2011-001001


FrancoAngeli is a member of Publishers International Linking Association a not for profit orgasnization wich runs the CrossRef service, enabing links to and from online scholarly content