smoking logosmoking.

Can we lie with statistics?

Purpose
The goal of the dataset is to figure out if smoking is good or bad for your health. It turns out that there is a counter intuitive effect in the dataset. If you ignore age, smoking seems to extend your life.
Links

This dataset is used in a number of places on our website.


Source
This dataset was originally found in the mosiac R package.
Contents

Name Description
outcome Was the person still alive after 10 years.
smoker Was the person a smoker.
age The age of the person.
Download

You can download the dataset from the commandline.


wget https://calmcode.io/static/data/smoking.csv

You can also download it directly.