Abstract
With regards to the Bayesian, we have developed an approach using Jeffreys prior and extension Jeffreys prior with covariate obtained by using Gauss quadrature method. This is also done for maximum likelihood estimator to estimate the parameters of the covariate of the Weibull regression distribution given shape with Type I censored data. It is seen that the estimators obtained are not available in closed forms although they can solve it using suitable numerical methods. The comparison criteria are the mean square errors. The performance of these three estimates is assessed using simulation, considering various sample sizes, several specific values of Weibull shape parameter. The results show that extension Jeffreys prior is a better estimator than others.