Skip to main content
Figure 4 | BMC Bioinformatics

Figure 4

From: MAID : An effect size based model for microarray data integration across laboratories and platforms

Figure 4

Quantile-Quantile plot. Gene by gene testing for the homogeneity of study effects. Overall test results are shown by the Quantile-Quantile plot of the observed (black curve) vs expected Q quantiles (red curve), the expected Q values are from the χ ( l − 1 ) 2 MathType@MTEF@5@5@+=feaagaart1ev2aaatCvAUfKttLearuWrP9MDH5MBPbIqV92AaeXatLxBI9gBaebbnrfifHhDYfgasaacPC6xNi=xH8viVGI8Gi=hEeeu0xXdbba9frFj0xb9qqpG0dXdb9aspeI8k8fiI+fsY=rqGqVepae9pg0db9vqaiVgFr0xfr=xfr=xc9adbaqaaeGaciGaaiaabeqaaeqabiWaaaGcbaGaeq4Xdm2aa0baaSqaaiabcIcaOiabdYgaSjabgkHiTiabigdaXiabcMcaPaqaaiabikdaYaaaaaa@339B@ distribution, where l designates the number of experiments. The difference between the observed and the expected Q quantiles are large and show that a random effect model should be considered for data integration.

Back to article page