Does nature have joints worth carving? A discussion of taxometrics, model-based clustering and latent variable mixture modeling.

摘要: Taxometric procedures, model-based clustering and latent variable mixture modeling (LVMM) are statistical methods that use the inter-relationships of observed symptoms or questionnaire items to investigate empirically whether underlying psychiatric psychological construct is dimensional categorical. In this review we show why results such an investigation depend on characteristics (e.g. symptom prevalence in sample) sample clinical, population sample). Furthermore, three differ with respect their assumptions therefore require different types a priori knowledge about inter-relationships. We argue choice method should optimally match make existing data analyzed.