Bayesian hierarchical models for multivariate mixed responses with repeated measures: a case study in arterial occlusive disease

Dataset Information The dataset (Arterial Disease data Wide.sav) contains patient information related to repeated measures on three numerical (continuous variables) and a categorical variable. This data is used to demonstrate a Bayesian hierarchical mixed response model in longitudinal data. Key features: PatientID: Identification of Patients Y11, Y12, Y13, and Y14: Patient’s Disease severity score Y1, Y2, Y3, and Y4: Health status X1, X2, X3, and X4: Patient's reduced cuff pressure (RCP) measurement U1, U2, U3 and U4: patient's ultrasound reading measurement Purpose: This dataset is intended to present a valuable statistical modeling application and comparison of Bayesian methods for complex longitudinal data, utilizing statistical modeling such as Bayesian hierarchical models for mixed (binary and continuous) responses, with a focus on joint modeling, prediction, understanding contributing factors, and potentially optimizing advanced methods for complex data in healthcare settings. File Format: SPSS dataset with wide format. No missing values occurred in the data.