In this article, we will use randomly censored data and to discuss both Bayesian and classical methods to the estimating parameters the inverse Pareto distribution (IPD). We derive the Bayes and maximum likelihood methods to obtain the parameters estimators. Asymptotic confidence intervals for the parameters are computed by using the observed Fisher information matrix. Using gamma informative priors, Bayes estimators for the parameters are derived under the (LINEX) loss function. For Bayesian estimates, the method of Markov Chain Monte Carlo (MCMC) is employed. In addition, using (MCMC) techniques, credible intervals with the largest posterior density for the parameters are generated. A simulation study compares how well each estimators performs. Lastly, two real datasets are taken into consideration for demonstration.