A Bayesian Approach to Robust Modeling of Skewed Biomedical Data

To demonstrate the empirical applicability of Bayesian Log-symmetric regression models, firstly we used the AIS (Australian Institute of Sport) dataset, freely accessible and widely used in statistical modelling. The data includes physioLogical and anthropometric measurements collected from 202 top-level athletes (102 females and 100 males) representing different sports disciplines. Secondly, to further illustrate the practical applicability of the Bayesian Log-symmetric regression framework, we employed the Pima Indians Diabetes dataset, a widely recognized medical dataset available in the UCI Machine Learning Repository. This dataset is originally from the National Institute of Diabetes and Digestive and Kidney Diseases. The objective of the dataset is to diagnostically predict whether or not a patient has diabetes, based on certain diagnostic measurements included in the dataset. Several constraints were placed on the selection of these instances from a larger database. In particular, all patients here are females at least 21 years old of Pima Indian heritage. The dataset consists of diagnostic measurements for 768 female patients of Pima Indian heritage, aged 21 years or older. The primary objective of this dataset is to predict the onset of type 2 diabetes based on various biomedical indicators.