In the field of animal breeding, several traits are of discrete nature and usually scored as count data. In this study, a hierarchical Bayesian model is proposed for analysis of zero-inflated data applied to the number of still born per sow. The procedure is tested using simulated data and then applied to a real data set. The results show that although differences between the mixture and a regular Poison model when all sires were considered were small, noticeable changes in the ranking were observed in the top sires, especially those with large numbers of zero count. Bayesian mixture modeling offers a flexible procedure for analysis of count data with excess zeros and should be used to avoid bias in the ranking of candidates for selection.
Proceedings of the World Congress on Genetics Applied to Livestock Production, Volume , , 24.08, 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.