Fifteen blanks were analyzed for serum samples, and the blank values, adjusted to a nominal sample size of 2 g and a mean lipid value of 0.69%, were 0.87 and 2.12, 0.00 and 0.09, 0.12 and 0.23, 0.80 and 0.99, and 0.00 and 3.3 (ng g 1 lw) for TBB, TBPH, BB-153, BDE-153, and DBDPE, respectively.
Eighteen blanks were performed for milk samples, and the median and mean values, adjusted to a nominal sample size of 5 g and a mean lipid value of 2%, were 0.15 and 0.23, 0.00 and 0.05, 0.02 and 0.03, 0.14 and 0.26, and 0.00 and 0.09 (ng g 1 lw) for TBB, TBPH, BB-153, BDE-153, and DBDPE, respectively.
For each foam material, three different nominal sample sizes (10 mm, 17 mm and 35 mm) were tested.
Student t-tests (for continuous variables with normal distribution), Fisher's exact test (for nominal data, small sample size), and Mann Whitney U test (for ordinal or continuous data without normal distribution) will be used to determine differences between the intervention and control group at baseline.
We showed that the difference between empirical and nominal levels widens when sample size decreases, especially when the probability for a given response category is low in a group of clusters with the same covariate vector.
Fifth, the median of the type I error rates becomes more close to the prespecified nominal level as the total sample size n increases, whilst at the same time the variability of the type I error rates decreases.
The type I error rates of the non-parametric bootstrap test are close to the given nominal level (α=0.05) when the sample size reaches 300, and 500 for the asymptotic normal distribution statistic.
When baseline imbalance is in the opposite direction from the treatment effect, ANCOVA corrects the resulting bias by producing an adjusted treatment effect that is larger than the nominal treatment effect, and ANCOVA therefore has greater power to detect this effect than ANOVA has to detect the nominal effect, at the same sample size.
We conduct simulation studies to demonstrate that the proposed sample size maintains the nominal power and type I error under a wide spectrum of trial configurations.
On the contrary, when the design effect value is below 1, the power is larger than the nominal one, allowing reducing the required sample size.
For a nominal statistical power of 80%, the required sample size was utilized for each of these standardized effect sizes: 394, 64 and 26 per group, respectively.
