An approximate best prediction approach to small area estimation for sheet and rill erosion under informative sampling (Q2233141)

The authors propose a procedure of estimation for sheet and rill erosion in the regions of the Boone-Raccoon River Watershed. The procedure is based on weighted estimating equations arising from a specified model. The profile pseudo maximum likelihood estimator is used to construct an area-level model. The EM algorithm for parameter estimation is constructed by using the approximate predictive distribution. One of the advantages of the proposed approach is robustness which may come at the expense of a loss of efficiency if the area sample sizes are too small. The authors validate properties of the procedure through simulation. For more details see [\textit{J. N. K. Rao} and \textit{I. Molina}, Small area estimation. 2nd edition. Hoboken, NJ: John Wiley \& Sons (2015; Zbl 1323.62002)].