Alternative methods focus on modelling patterns of agreement, and log-linear models [7] and latent trait and latent class models [8] have been widely used for this purpose.
Methods based on modelling sound propagation are useful, but they need to be checked against empirical data to avoid biased results.
Compared with the related studies, we have also shown the advantageous features in the proposed method on modeling and algorithm performance.
These are, e.g., approaches based on a spatial covariance model [5] or multichannel nonnegative matrix factorization (NMF) methods based on modeling complex Gaussian distributions [6, 7].
One class of methods focuses on modeling and correcting for bias involved in generating read counts, such as mapping bias favoring the reference alleles [ 20– 20].
For data clustering, the clustering stability methods on model selection techniques have been investigated in [14].
The authors examined the influence of these methods on model composition.
Also, all methods tend to detect more interacting SNPs with strong main effects than those with weak main effects (power of all the methods on models 2 and 3 is generally higher than on models 1, 4, and 5).
An extensive literature exists composed of simulation studies that have evaluated the performance of different inference methods on model trees, investigating the branch length conditions wherein long-branch effects lead to misleading results.
They used ab initio methods on model systems and concluded that the energy of these short bonds is high and therefore they must be stabilized by 'interatomic forces in the crystal' which they did not specify.
