Inspiration

E-cigarettes have gotten incredibly popular amongst the youth and middle-aged people; we wanted to investigate if we could predict prevalence for diseases such as heart attacks, stroke, heart disease and cancer.

What it does

Logistic regression models built in R that tested for covariates including cigarette and e-cigarette usage

How we built it

R - cleaning and creating models

Challenges we ran into

Cleaning CDC data and finding relevant covariates and enough data points with relevant entries

Accomplishments that we're proud of

Finishing the datathon and creating decent models

What's next for Are E-Cigarettes Safer?

A further analysis of supervised learning methods with greater amounts of relevant data

Built With

Share this project:

Updates