Chapter 17 Random Intercept Models

Example Data

Radon is a radioactive gas that naturally occurs in soils around the U.S. As radon decays it releases other radioactive elements, which stick to, among other things, dust particles commonly found in homes. The EPA believes radon exposure is one of the leading causes of cancer in the United States.

This example uses a dataset named radon from the rstanarm package. The dataset contains \(N=919\) observations, each measurement taken within a home that is located within one of the \(J=85\) sampled counties in Minnesota. The first six rows of the dataframe show us that the county Aitkin has variable levels of \(log(radon)\). Our goal is to build a model to predict \(log(radon)\).

data(radon, package="rstanarm")
head(radon)
##   floor county  log_radon log_uranium
## 1     1 AITKIN 0.83290912  -0.6890476
## 2     0 AITKIN 0.83290912  -0.6890476
## 3     0 AITKIN 1.09861229  -0.6890476
## 4     0 AITKIN 0.09531018  -0.6890476
## 5     0  ANOKA 1.16315081  -0.8473129
## 6     0  ANOKA 0.95551145  -0.8473129