The “stan_rhat” Function in R

• Package: rstan

• Purpose: Computes the potential scale reduction factor (R-hat) for Stan model parameters.

• General class: Diagnostic

• Required argument(s):

• object: Stanfit object containing the samples.

• Notable optional arguments:

• ...: Additional arguments passed to the function.

• Example:

• # Load the rstan package
  library(rstan)
  
  # Fit a simple linear regression model
  model_code <- "
  data {
  int<lower=0> N;
  vector[N] y;
  }
  parameters {
  real mu;
  real<lower=0> sigma;
  }
  model {
  y ~ normal(mu, sigma);
  }
  "
  model_data <- list(N = 100, y = rnorm(100))
  fit <- stan(model_code = model_code, data = model_data, chains = 4)
  
  # Compute R-hat for all parameters
  rhat <- stan_rhat(fit)
  print(rhat)

• This example shows how to use the stan_rhat function from the rstan package to compute the potential scale reduction factor (R-hat) for parameters in a Stan model (fit). The function takes the Stan object fit as the x argument and allows optional arguments (...) to be passed for customization.