Skip to main content

Table 4 Expanding contrasts from two to three groups. Logistic regression models testing the significance of a difference between normal colon and primary tumor (β1) for tag TGCTGCCTGT from Table 2. In the first model, only data from the four libraries directly involved are used. In the second model, data from the four cell line libraries are also included, providing a more stable estimate of the overdispersion parameter φ.

From: Overdispersed logistic regression for SAGE: Modelling multiple groups and covariates

Model 1: Two Groups = 8.938e - 05 df = 2
Coefficients Estimate (s.e) t-value p-value
β 0 -11.484 2.309 -4.973 0.038
β 1 2.681 2.388 1.123 0.378
Model 2: Three Groups = 1.160e - 04 df = 5
Coefficients Estimate (s.e) t-value p-value
β 0 -11.484 2.574 -4.462 0.007
β 1 2.676 2.661 1.005 0.361
β 2 3.020 2.604 1.159 0.299