Categorical estimation is different, so we can try such as Bayesian estimation, non linear estimation, dwls, wls, wlsmv, robust maximum likelihood, moreover we can try bootstrap, jacknife and cross validation . eventu we can compare these methods
Each method has its strong and weak points. The research problem, objectives of the problem and the assumptions required for each method are the main factors on the selection of a suitable method.
Please refer to:
Z. A. Al-Hemyari, H. Al Dabag and A. Al-Humairi(2018). A Class of Always Pooling Shrinkage Testimators for the Weibull Model. Int. J. of Mathematics in Operational Research.
Z. A. Al-Hemyari and H. A. Al-Dabag (2016). Two classes of Bayes-shrinkage estimators for
Weibull lifetime model. Int. J. of Data analysis Techniques and Strategies, Vol.8, No.2, pp.161-182.