This paper is about differential gene expression measured by transcript counting methods such as SAGE or MPSS. It introduces two significance tests for detection of differential expressed tags: frequentist and Bayesian. Under the frequentist view, it is proposed a test that computes the critical level as a function of each tag total frequency. Under the Bayesian view the Full Bayesian Significance Test is used considering the logistic normal distribution. The two proposed significance levels, the frequentist and the Bayesian, are compared for a data set with four libraries. The linking function between them is a Beta distribution function with mean 0.39 and standard deviation 0.30. |