This report explores the use of regression models for estimating health status of schizophrenic patients from a Bayesian perspective. The aims are: to obtain a set of values of health states of the EQ-5D based on self-assessed health from a sample of schizophrenic patients; and to analyze the differences in the health status and in patients' perceptions of their health status between four mental health districts in Spain. The authors develop two linear models with dummy variables. The first model seeks to obtain an index of the health status of the patients using a visual analog scale as a dependent variable and the different dimensions of EQ-5D as regressors. The second model enables analysis of the differences between the self-assessed health status in the different geographic areas and also the differences between the patients' self-assessed health states, irrespective of their actual health state, in the different geographic areas. The analysis is done using a Bayesian approach with Gibbs sampling (computer program WinBUGS 1.4). Data concerning self-assessed EQ-5D with visual analog scale from four geographic areas of schizophrenic patients were obtained for the purposes of this analysis. The health status index for this sample was obtained and the differences for this index between the four geographic areas were analyzed. The study reveals variables that explain the differences in patients' health status and health state assessment. Four possible scenarios are considered.