Skip to main content
Fig. 1 | BMC Bioinformatics

Fig. 1

From: Simulating ComBat: how batch correction can lead to the systematic introduction of false positive results in DNA methylation microarray studies

Fig. 1

a Different case and control sample distributions of n = 48 on six chips (red, case; dark grey, control). b Systematic increase of the number of factor levels for one corrected factor. The vertical red line shows the factor level with the first false FDR-significant result. c Mean p-value decrease for different sample sizes in combination with a systematic increase of the number of factor levels. d Number of FDR-significant CpG sites with a systematic increase of factor levels for the different Illumina arrays

Back to article page