أخذ عينات MCMC وتشخيصها

ما هو MCMC؟

نموذج Stan بسيط

# library(rstan)
#
# stan_code <- '
# data {
#   int<lower=0> N;
#   vector[N] y;
# }
# parameters {
#   real mu;
#   real<lower=0> sigma;
# }
# model {
#   mu    ~ normal(0, 10);   // prior
#   sigma ~ exponential(1);   // prior
#   y     ~ normal(mu, sigma); // likelihood
# }
# '

استدعاء stan() لأخذ العينات

# library(rstan)
# options(mc.cores = parallel::detectCores())
#
# y <- c(2.1, 1.8, 2.4, 1.9, 2.3, 2.0, 1.7, 2.2)
# stan_data <- list(N = length(y), y = y)
#
# fit <- stan(
#   model_code = stan_code,
#   data       = stan_data,
#   chains     = 4,
#   iter       = 2000,
#   warmup     = 1000,
#   seed       = 42
# )

print(fit) — جدول التلخيص

# print(fit)
#
# Example output:
#       mean se_mean   sd  2.5%   25%   50%   75%  97.5%  n_eff Rhat
# mu    2.05    0.00 0.15  1.76  1.95  2.05  2.15   2.34   3842    1
# sigma 0.22    0.00 0.06  0.13  0.18  0.21  0.25   0.37   3521    1
# lp__  4.38    0.02 1.01  1.60  3.91  4.71  5.18   5.50   2148    1

معيار تقارب Rhat

# Check Rhat for all parameters:
# s <- summary(fit)$summary
# rhat_vals <- s[, 'Rhat']
# cat('Max Rhat:', max(rhat_vals, na.rm = TRUE), '
')
# if (any(rhat_vals > 1.01, na.rm = TRUE)) {
#   warning('Convergence issue detected!')
# } else {
#   cat('All Rhat < 1.01 — chains converged
')
# }

n_eff — حجم العينة الفعّال

# s <- summary(fit)$summary
# n_eff_vals <- s[, 'n_eff']
# total_samples <- 4 * 1000   # chains * post-warmup iter
# ratio <- n_eff_vals / total_samples
# cat('n_eff ratio (mu)   :', round(ratio['mu'], 2), '
')
# cat('n_eff ratio (sigma):', round(ratio['sigma'], 2), '
')

traceplot() للتقارب البصري

# library(rstan)
#
# traceplot(fit, pars = c('mu', 'sigma'), inc_warmup = FALSE)
#
# Good traceplot characteristics:
# - All 4 chains overlapping completely (same range)
# - No visible drift or trend
# - Rapid mixing (values jump around quickly)
# - No flat regions (stuck sampler)
cat('A healthy traceplot looks like a fuzzy caterpillar
')

pairs() للارتباطات اللاحقة

# pairs(fit, pars = c('mu', 'sigma'))
#
# What to look for:
# - Elliptical clouds: mild correlation (OK)
# - Banana / funnel shapes: reparameterization needed
# - Red dots (divergences): geometry problem in posterior
#   => increase adapt_delta: stan(..., control=list(adapt_delta=0.95))
cat('Red dots in pairs() indicate divergent transitions — investigate!
')

استخراج العينات اللاحقة

# mu_samples <- extract(fit, pars = 'mu')$mu
# cat('Posterior mean :', mean(mu_samples), '
')
# cat('95% CI:', quantile(mu_samples, c(0.025, 0.975)), '
')
# cat('P(mu > 2):', mean(mu_samples > 2), '
')
# hist(mu_samples, main = 'Posterior of mu', xlab = 'mu', col = 'steelblue')

تشغيل ShinyStan للتشخيص التفاعلي

# install.packages('shinystan')
# library(shinystan)
#
# shinystan::launch_shinystan(fit)
#
# ShinyStan tabs:
# - Diagnose: Rhat, n_eff, divergences, energy
# - Explore:  marginal posteriors, scatter plots
# - Model:    Stan code, data
# - NUTS:     step size, tree depth per chain

إصلاحات شائعة للتقارب

# Re-run with higher adapt_delta to reduce divergences:
# fit2 <- stan(
#   model_code = stan_code,
#   data       = stan_data,
#   chains     = 4,
#   iter       = 4000,
#   warmup     = 2000,
#   control    = list(adapt_delta = 0.95, max_treedepth = 12),
#   seed       = 42
# )

تحقق سريع: حد Rhat

مراجعة أخذ عينات MCMC وتشخيصها