The motivation for this project is to build an R package that outputs necessary data frames relevant to obesity costs, where the clients could easily manipulate the output using difference parameters, e.g. relative risks for each illnesses. This is in conjunction with another research project that estimated the state-level economic costs of obesity in the United States. Therefore, this package makes the calculated estimates, corresponding plots, and future predictions easily accessible. This R package is currently being refined, but once published it will serve to benefit many, the primary beneficiaries being statisticians and those in the actuarial field. This is because the data frames produced required many distinct data sources, as well as statistical methods to ensure the validity of estimates produced. Having this granularity of data for obesity could be of use to those in the life/health actuarial field since analysis can be done on the trends seen throughout the time period. The basic structure of the R package was inspired by the ‘Lahman’ R package, which offers many different outputs of baseball statistics from a wide range of years. The goal was to emulate our package into something similar, so that our large amount of information could be acquired easily and intuitively.
Authors: Selina Zang, Thomas Woods
Advisor: Tatjana Miljkovic, Statistics
You must be logged in to post a comment.