tpoisot
commented
10 years ago As mentionned in the introduction, modularity finding methods differ often by their choice of criterion to optimize. Furthermore, for obvious reasons, the criteria used for optimisation cannot be used a posteriori as a goodness-of-fit measure. However, and perhaps the referee mis-read the text, I never use Qr not Qr' to optimise modularity. This is now clarified in the abstract and Intro ¶2. The sense of the measure, as now stated in Measure ¶4.
Adressed in b68057a
I am not sure how useful the whole idea of an a posteriori measure is. The author stresses that the measure is not aimed at maximizing modularity in an algorithm, but just to select which algorithm to use. This is not convincing: either the measure reflects the property of interest, then it should be maximized in the first place in the algorithm to find the best partition; or it is not a sensible measure, then it cannot be used for selection at all. The approach proposed here appears very inefficient and almost certainly not to give the best partition. Furthermore, any measure of modularity could be calculated a posteriori or during modularity optimization. The description of this index specifically as an a posteriori measure gives no real sense, without additional data or simulations showing that it is more meaningful than others. If the functional meaning was demonstrated, there could be some value in using it a posteriori for those who don’t have access to source algorithms.