PubMed · 7326546
The source did not provide an abstract. Follow the original record for more information.
Explore connections, maps & timelines
E S Paykel. 1981. Have multivariate statistics contributed to classification?. https://doi.org/10.1192/bjp.139.4.357
Cite the original work for its findings. Save a collection to share your selection of sources.
KEEP EXPLORING
BACKGROUND: Previous factor analytic studies of patients with schizophrenia have consistently demonstrated the presence of 3 psychopathological domains labeled positive, negative, and disorganized. This study examined whether similar domains can be seen in disorders other than schizophrenia, and the degree to which such domains are independent of diagnostic categorization. METHODS: Data from the Diagnostic and Statistical manual of Mental Disorders, Fourth Edition (DSM-IV) field trial involving 221 patients with schizophrenia and 189 patients with nonschizophrenia diagnoses were factor analyzed to study the nature of psychopathological domains in the 2 groups. Differential associations between each domain and selected clinical variables were assessed. RESULTS: Factor analysis yielded a similar 3-factor model of positive, negative, and disorganization domains for patients with schizophrenia as well as other diagnoses. Differential associations found between individual domains and clinical variables (premorbid functioning and negative domain; absence of remissions and disorganization domain) were similar in both schizophrenia and nonschizophrenia groups. CONCLUSIONS: The 3 psychopathological domains previously described in schizophrenia are not specific for that diagnosis. Differential associations found between individual domains and clinical variables were not limited by diagnostic categorization. The results suggest that these domains are not unique to schizophrenia and may each correspond to a discrete pathophysiologic condition.
Explore the source record for details and available documents.
We describe a linear network that models correlations between real-valued visible variables using one or more real-valued hidden variables-a factor analysis model. This model can be seen as a linear version of the Helmholtz machine, and its parameters can be learned using the wake-sleep method, in which learning of the primary generative model is assisted by a recognition model, whose role is to fill in the values of hidden variables based on the values of visible variables. The generative and recognition models are jointly learned in wake and sleep phases, using just the delta rule. This learning procedure is comparable in simplicity to Hebbian learning, which produces a somewhat different representation of correlations in terms of principal components. We argue that the simplicity of wake-sleep learning makes factor analysis a plausible alternative to Hebbian learning as a model of activity-dependent cortical plasticity.