Skip to main content
Figure 1 | BMC Bioinformatics

Figure 1

From: Controlling false discoveries in high-dimensional situations: boosting with stability selection

Figure 1

Covariate effects. Effect types range from oscillating functions (f 1), over quadratic functions (f 2), arbitrary smooth function (f 3 and f 4), cosine functions (f 5), and piecewise linear functions (f 6), to linear functions (f 7 and f 8). For two influential covariates we used f 1 and f 2, for three influential covariates we used f 1 to f 3 and for eight influential covariates we used all functions.

Back to article page