Gamma prior on the total noise variance. A Gamma prior is assumed for the hyperparameter . This reflects our prior knowledge that is a lower bound for the total noise variance. The total noise variance is unlikely to be greater than the total variance of the data, which is approximately unity because of normalisation, see Equation 7.
Cooke et al. BMC Bioinformatics 2011 12:399 doi:10.1186/1471-2105-12-399