In the fields of epidemiology, ecology and medical science often we encounter with hierarchical models where maximum likelihood estimation can become very challenging. Gompertz state space model and quantile regression model are such examples. The most common approach to deal with these types of hierarchical models is Bayesian inference. However, for a small sample size Bayesian inference largely depends on the prior distribution, which can lead to a wrong conclusion for a misspecified prior. Data cloning an alternative approach proposed by Lele, Dennis, and Lutscher (2007) provides maximum likelihood estimation by using Markov Chain Monte Carlo (MCMC) approach. This estimation procedure is invariant to the choice of prior distribution and thus eliminates the subjectivity of Bayesian approach. Using this method, inferences can be drawn for very complex hierarchical models with any standard MCMC software.