When analyzing psychometric surveys, some design and sample size limitations challenge existing approaches. Hierarchical clustering, with its graphics (heat maps, dendrograms, means plots), provides a nonparametric method for analyzing factorially-designed survey data, and small samples data. In the present study, we demonstrated the advantages of using hierarchical clustering (HC) for the analysis of non-higher-order measures, comparing the results of HC against those of exploratory factor analysis. As a factorially-designed survey, we used the Identity Labels and Life Contexts Questionnaire (ILLCQ), a novel measure to assess identity as a bridging construct for the intersection of identity domains and life contexts. Results suggest that, when used to validate factorially-designed measures, HC and its graphics are more stable and consistent compared to EFA.
The analysis of bridging constructs with hierarchical clustering methods: An application to identity / Farrelly, Colleen M.; Schwartz, Seth J.; Lisa Amodeo, Anna; Feaster, Daniel J.; Steinley, Douglas L.; Meca, Alan; Picariello, Simona. - In: JOURNAL OF RESEARCH IN PERSONALITY. - ISSN 0092-6566. - 70:(2017), pp. 93-106. [10.1016/j.jrp.2017.06.005]
The analysis of bridging constructs with hierarchical clustering methods: An application to identity
Lisa Amodeo, Anna;Picariello, Simona
2017
Abstract
When analyzing psychometric surveys, some design and sample size limitations challenge existing approaches. Hierarchical clustering, with its graphics (heat maps, dendrograms, means plots), provides a nonparametric method for analyzing factorially-designed survey data, and small samples data. In the present study, we demonstrated the advantages of using hierarchical clustering (HC) for the analysis of non-higher-order measures, comparing the results of HC against those of exploratory factor analysis. As a factorially-designed survey, we used the Identity Labels and Life Contexts Questionnaire (ILLCQ), a novel measure to assess identity as a bridging construct for the intersection of identity domains and life contexts. Results suggest that, when used to validate factorially-designed measures, HC and its graphics are more stable and consistent compared to EFA.File | Dimensione | Formato | |
---|---|---|---|
Farrelly...Picariello_Analysis of bridging constructs.pdf
accesso aperto
Licenza:
Accesso privato/ristretto
Dimensione
2.17 MB
Formato
Adobe PDF
|
2.17 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.