The purpose of this study is to identify socio-demographic factors affecting thernbipolar disorder patients. The data included in this study are a cross sectional datarncollected by the Butajira mental health project. In this study, 828 psychiatric patientsrnwere included, of which 511(61.75%) belong to the non bipolar disorder symptom,rn218(26.3%) belong to the moderate bipolar disorder symptom and 99(12%) belongrnto severe bipolar disorder symptom. In the analysis of data, polytomous logisticrnregression and multiple discriminant analysis are employed. It is found that place ofrnresidence, quality of life, marital status, number of children, and the interactionrnbetween residence and quality of life are significantly associated with the severity ofrnbipolar disorder.rnThe polytomous logistic regression provides higher percentage of correctlyrnclassifying psychiatric patients into no, moderate, and severe bipolar disorderrnsymptom groups (61.7%) as compared to multiple discriminant analysis (50.8%). Sornthat polytomous logistic regression is more efficient than that of multiplerndiscriminant analysis in classifying of the psychiatric patients into the no, moderaternand severe bipolar disorder symptom groups. This study identifies that the potentialrnsocio-demographic factors such as place of residence, quality of life, number ofrnchildren, marital status, and age of the patients and the interaction betweenrnresidence and quality of life affects bipolar disorder patients