The partitioning of surrogate parents into their paternal and maternal clusters was the principle computation bottleneck and was affected by the dataset size, effective population size, and the degree of relatedness among the individuals.
This indicates that the model's reliability readout (i.e., trend between predictive performance and the AD measure) is not being affected by the specific dataset being evaluated, but instead the AD is robust enough to describe the predictive reliability across the data.
For string-based assembler, the time and memory cost is approximately proportionate to dataset size, although it is also affected by the complexity of dataset.
The second important consideration is the robustness of SLEA with regard to changes in the cohort and how it is affected by the sizes of the datasets (that is, the number of samples included).
Similarly, inferences based on such data may thus also be substantially affected by the choice of dataset, its characteristics and limitations.
Compared with the traditional feature extraction methods and classifiers, the proposed models are less likely affected by the imbalance of the dataset.
Developing a statistical model for a maternally affected trait requires a careful balance between sufficient predictive ability and computational practicality, which in turn are affected by the size of the dataset, potential biases in data recording, the trait in question, computational facilities and the amount of time in hand.
In this study, we found that accuracy of branch length estimation is affected by the length of the dataset, the length of the branch and of the other branches in the tree, the depth of the branch, and the statistical framework in which branch lengths are estimated.
Overall, GS accuracies were least affected by the imputation method for dataset version NA20, and most affected by the imputation method for dataset version NA70.
The exact age at which trends change is significantly affected by the age-range of the dataset.
