Data
====

1. radon.data.R
  - J     : number of counties
  - N     : number of observations
  - county: county number
  - radon : radon measurement
  - u     : county-level uranium measure
  - x     : house-level first-floor indicator
  - y     : log of the home radon level

Models
======

1. Multilevel model with varying intercept
  radon_vary_intercept_a.stan      : lmer(y ~ x + (1 | county))
  radon_vary_intercept_c.stan      : lmer(y ~ x + u + (1 | county))
  radon_vary_intercept_b.stan      : lmer(y ~ x + (1 | county))
  radon_vary_intercept_nofloor.stan: lmer(y ~ u + (1 | county))
  radon_vary_intercept_floor.stan  : lmer(y ~ u + x + (1 | county))
  radon_vary_intercept_floor2.stan : lmer(y ~ u + x + x_mean + (1 | county))

2. Above models with Matt trick
  radon_vary_intercept_c_chr.stan      : lmer(y ~ x + u + (1 | county))
  radon_vary_intercept_nofloor_chr.stan: lmer(y ~ u + (1 | county))
  radon_vary_intercept_floor_chr.stan  : lmer(y ~ u + x + (1 | county))
  radon_vary_intercept_floor2_chr.stan : lmer(y ~ u + x + x_mean + (1 | county))

3. Other
  finite_populations.stan : lmer(g ~ u_1 + u)  
  multiple_comparison.stan: lmer(y ~ theta)
  r_sqr.stan              : lmer(y ~ 1 + (1 + x | county))