Reproduce Analysis with Bayesian approach

[aldoMsc]

import pymc as pm
with pm.Model() as model:
alpha = pm.Normal("alpha", 0, 10)
betas = pm.Normal("betas", 0, 1, shape=n_predictors)
sigma = pm.HalfNormal("sigma", 5)
mu = alpha + pm.math.dot(X_std, betas)
y_obs = pm.Normal("y_obs", mu=mu, sigma=sigma, observed=y)
idata = pm.sample(draws=2000, tune=1000, target_accept=0.9, return_inferencedata=True)

Model includes explicit priors on parameters.

Posterior inference performed (MCMC/VI/analytical) and summarized.

Posterior predictive checks performed.

Diagnostics reported (R̂, ESS, divergences).

Sensitivity to priors assessed.