Genes differentially expressed in different tissues, during development, or during specific pathologies are of foremost interest to both basic and pharmaceutical research. So called transcript profiles or digital Northerns are generated routinely by partially sequencing thousands of randomly selected clones from relevant cDNA libraries. Differentially expressed genes can then be detected from variations in the counts of their cognate sequence tags. The first systematic study on the influence of random fluctuations and sampling size on the reliability of this kind of data was presented by Stephane Audic and Jean-Michel Claverie. They established a rigorous significance test and demonstrated its use on publicly available transcript profiles. Their method(Audic`s Test) became popular but it also has practical limitations because it is affected only by sampling sizes. Furthermore they thought the probability distribution they found was not specified yet but it turned out to be the negative binomial distribution. So we can utilize the statistics and properties of it to make computations less complex. On our work, we give a combinatorial proof of Audic`s formula so that we can apply their result to more general cases where the test is not controlled only by sampling sizes but also by other experimental factors.