The covariates included in the analysis were evaluated using both forward and reverse stepwise methods.
The performance of the NN analysis was evaluated using a statistical indicator (the coefficient of multiple determination), and by examination of the error patterns.
PFS for the primary analysis was evaluated using the Kaplan Meier method with associated medians and 90% one-sided CI.
The relevance analysis was evaluated using two supervised measures: linear correlation and symmetrical uncertainty.
The goodness of fit by the two-model analysis was evaluated using AIC.
Convergence and mixing of the chain of each analysis was evaluated using Tracer v1.6.1 (http://tree.bio.ed.ac.uk/software/tracer) to check that the ESS values were all superior to 200.
Representatively of the sample with HR-QoL measurements for the non-responders (non-respondent analysis) was evaluated using χ2 tests to compare categorical data, and the Student's t-test or the Mann-Whitney U test for continuous data.
The shortest fatigue life from Finite Element and fatigue analysis was evaluated using the starting point of WEL, and the results were consistent with those from contact fatigue tests.
The difference between BMP4- and vehicle-treated samples in cell proliferation and area analysis was evaluated using the Mann–Whitney test with GraphPad Prism 4 (GraphPad Software, La Jolla, CA, USA).
A new forensic 140-SNP genotyping system from Qiagen, designed for massively parallel sequencing (MPS) analysis, was evaluated using the Ion PGM™ MPS system.
Goodness of fit by nonlinear least squares analysis was evaluated using the Akaike information criterion (AIC) and model selection criterion (MSC).
