This is a repository for work done at the Summer Institute of Biomedical Data Science at UC Irvine, sponsored by the National Institutes of Health.

The program culminated in a team biostatistics and data science research project guided by an advisor. Our project was to create a predictive statistical model for stress using longitudinal biophysical and contextual data of pregnant mothers.

data

• All biophysical, contextual, and demographic data we received with which we worked, including data dictionaries.

scripts

• Ordered set of scripts meant to be run together that perform data processing and cleaning as well as modeling, selection, validation, and evaluation.

The base directory also contains the .pdf final report which was presented at the final research symposium.