After global normalization of data from separate sessions, single-subject statistical contrasts were computed using a parametric general linear model (Buchel et al., 1998; Friston et al., 1998).
The statistical examination of the six dependent variables Yit shows that they are all in continuous form, normally distributed, and do not contain any outliers, so the use of a parametric linear model is appropriate [ 39].
For example, Long et al. [ 16] used a computer simulation and found that the predictive ability of a non-parametric smoother was superior to that of a parametric linear counterpart when non-additive effects were strong.
By using the weighted sum scalarization approach, we reformulate the linear semivectorial bilevel programming problem as a special bilevel programming problem, where the lower level is a parametric linear scalar optimization problem.
Therefore, we used a parametric test.
A comprehensive approach for real-time computations using a database of parametric, linear, projection-based reduced-order models (ROMs) based on arbitrary underlying meshes is proposed.
We analyzed the hybridization data using a two-stage parametric linear modeling approach (Methods).
Nevertheless, for the purpose of this paper, we will continue to use the parametric linear model paradigm (in fact the one-parameter Wald test is equivalent to the Student t-test) and not the non-parametric alternative, the Wilcoxon rank sum test.
Since the cost data were assumed to be non-normally distributed, p-values were estimated using a general linear model while employing non-parametric bootstrap analysis (5,000 replications).
