Estimation of parameters of the shifted Gompertz distribution using least squares, maximum likelihood and moments methods

Nonlinear least squares procedures for estimating the parameters of the shifted Gompertz distribution are proposed. Simulation studies are carried out to compare weighted and unweighted least squares methods, the maximum likelihood method and method of moments. This work concludes that least squares methods via weighting factors to estimate the parameters of this probability distribution give a better performance than unweighted least squares methods, showing the importance of weighting factors. Besides, results of this simulation study show that a good performance is obtained using the maximum likelihood method and the estimators obtained with more bias are those of the method of moments.