A two step derivative free procedure to estimate the expected information matrix is proposed, termed Simulated REML. Simulation on the realized data structure is followed by multiple regression of the Fisher quadratics on the simulated parameters and the expected information. An application to a single trait animal model is presented along with computing suggestions for implementation. Preliminary results of a simulation study are also presented.
Proceedings of the World Congress on Genetics Applied to Livestock Production, Volume XIII. Plenary lectures, molecular genetics and mapping, selection, prediction and estimation., , 472–475, 1990
|Download Full PDF||BibTEX Citation||Endnote Citation||Search the Proceedings|
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.