Skip to main content
Fig. 2 | Genetics Selection Evolution

Fig. 2

From: Semi-supervised learning for genomic prediction of novel traits with small reference populations: an application to residual feed intake in dairy cattle

Fig. 2

Average accuracy of genomic prediction for 252 animals in the testing set. Accuracy of genomic prediction was measured as the a correlation or b mean squared error between predicted and measured residual feed intake phenotypes, plotted against the size of the training set of animals with measured phenotypes. The results for each training set size were based on 100 replicates using \( n \) = 20, 60, …, 500 random samples from the full training set of 540 individuals with measured phenotypes. Error bars indicate the 95% confidence interval for each mean

Back to article page