Abstract
The paper explores the quantile regression model, a crucial tool in various scientific fields, focusing on characterizing conditional quantile forms in Tobit regression by estimating appropriate parameters from the lasso Bayesian theorem aspect. The study employs a novel Bayesian hierarchical priors model for the Gibbs sampler procedure, combines Rayleigh distribution with standard exponential, and investigates Bayesian quantile regression estimation for the Tobit model using MCMC and Gibbs sampler techniques. . The study employs a novel Bayesian hierarchical priors model for the Gibbs sampler procedure, combines Rayleigh distribution with standard exponential, and investigates Bayesian quantile regression estimation for the Tobit model using MCMC and Gibbs sampler techniques.The recommended technique outperforms other regression models in terms of variable selection prior due to its lower mean absolute error and mean square error
