The Current and Future Use of Ridge Regression for Prediction in Quantitative Genetics

Figure 5

The logarithm of the ratio of the median of the over 21 simulations, attained by ridge regression and the classical GWAS approach of RSR, for different combinations of training sample size (-axis), number of SNPs (-axis), trait heritability (-axis in the sub-plots), and fraction of SNPs with a causal effect (-axis in the subplots). Ridge parameter is chosen to maximize the median . Values truncated to lie between minus one (red) and plus one (green).