Skip to main content
Fig. 3 | BMC Medical Research Methodology

Fig. 3

From: A new statistical method for curve group analysis of longitudinal gene expression data illustrated for breast cancer in the NOWAC postgenome cohort as a proof of principle

Fig. 3

Distribution of case-control pairs for two curve groups stratified on spread in each time period. Plot of two of the most significant curve group variables, Z 132,with spread,p and Z 312,without spread,p , for the three time periods. These variables are the sum of gene expression differences X g,p for genes selected from curve group 132 (high values in middle period) based on data with spread and curve group 312 (low values in middle period) based on data without spread. The data with spread (without spread) are first used to select two sets of genes, one set for each of the two curve-group variables. We may calculate both Z 132,with spread,p and Z 312,without spread,p for all case-control pairs from all strata. Note that the difference between the two strata varies between the periods

Back to article page

BMC Medical Research Methodology

ISSN: 1471-2288

Contact us