The efficiency of the nonparametric discriminant analysis k-nearest neighbours method with different dissimilarity coefficients was evaluated based on molecular information. Two highly divergent populations were simulated. Forty individuals of each population and 32 dominant markers were evaluated. Barring the coefficient of Russel and Rao, the similarity coefficients of Jaccard, Nei and Li, Simple matching, Hamann, Yule, Roger and Tanimoto, and Ochiai all proved to be suitable options for the use in the k-nearest neighbours method.
Proceedings of the World Congress on Genetics Applied to Livestock Production, Volume , , 23.16, 2006
|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.