Methods For Categorical Data Analysis Research Articles

Origins of Comorbidity between Conduct and Affective Disorders

This analysis used methods of structural equation modeling to assess the extent to which comorbidity between conduct and affective disorders could be explained by (1) common or correlated causal factors that influenced both outcomes or (2) reciprocal causation between these conditions. Data were obtained during the course of a 16-year longitudinal study of a birth cohort of New Zealand children. The data analyzed comprised measures of conduct and affective disorders at ages 15 and 16 years and data on a series of antecedent childhood factors. Structural equation modeling suggested that a substantial component of the comorbidity between conduct and affective disorders arose because the risk factors associated with the development of conduct disorders in teenagers overlapped and were correlated with the risk factors for adolescent affective disorders; of the shared variance between conduct disorder and affective disorders, more than two thirds was explained by common risk factors. These conclusions were replicated using diagnostically scored measures and methods of categorical data analysis. Model extensions suggested an absence of direct causal pathways between conduct and affective disorders. A substantial amount of the correlation and comorbidity between conduct and affective disorders arises because the risk factors and life pathways that predispose adolescents to one outcome are also associated with the risk factors and life pathways that predispose adolescents to the other outcome. Nonetheless, even after control for common causal factors, there was evidence of some unexplained comorbidity between conduct and affective disorders.

Factors affecting the use of bus and rail services in a deregulated environment

In 1987, the NSW Government commenced deregulation of the long-distance bus industry in NSW. This immediately led to greater inter-modal competition and contestability within the context of changing passenger markets. This study utilises categorical data analysis methods to examine the emerging passenger markets of inter-modal competitors (bus and rail) and to assess the relative importance of socioeconomic and travel related variables which affect the use of bus and rail services along the high volume Sydney-Canberra and Sydney-North Coast corridors. Conclusions from the study indicate varied passenger markets within a relatively new contestable environment which are mode and corridor specific. Results are indicative of the need for competitors to develop marketing strategies conducive to the demands of the travelling public in order to enhance viability and commercial opportunities.

An analysis of psychiatric patient attributes in Salford using categorical data models

Much geographical work about mental illness has been aggregative in nature and, consequently, has ignored variation that might be attributed to individuals. The research reported here is intended to reverse this trend by applying the methods of categorical data analysis to the detailed patient histories contained in the Salford Psychiatric Case Register. The paper begins by reviewing the changing prevalence rates for various diagnoses and types of care in Salford between 1968 and 1986. In the light of this background log-linear data models are fitted to evaluate relationships between service usage and patient age, diagnosis and marital status and residential location at two survey points within the study period. Significant relationships are examined in terms of their temporal stability (such as the diagnosis of schizophrenia and a marital status of single) and instability (the changing role of the community psychiatric nurse) to isolate the main combinations of categories to influence the uptake of psychiatric services.