The results from three different approaches: the Average linkage method, the scree plot of within groups sum of squares, ratio of between-cluster variability and within-cluster variability, and the Multi-scale bootstrap of Ward's method are described and discussed below in (a), (b) and (c).
Moreover we performed a multi-scale bootstrap resampling approach (relative sample sizes of bootstrap replication of 20%) [21] to test whether clusters 1 3 are robust against variation in the data.
Confidence values using the approximately unbiased P value were generated from multi-scale bootstrap resampling.
Clusters were detected at P > 0.95 by the multi-scale bootstrap technique with 10000 iterations [ 19].
This test uses a multi-scale bootstrap technique that consists of generating sets of bootstrap replicates with varying sequence lengths and estimating the AU p-value from the change in the bootstrap probability values along the changing sequence length [ 28].
Pvclust provides two types of p-values to assess the uncertainty for each cluster: approximately unbiased (AU) p-value and bootstrap probability (BP) value, via multi-scale bootstrap re-sampling [ 35].
The p-values from this test are calculated using the multi-scale bootstrap technique and are less biased than those of the conventional methods such as the bootstrap probability (BP), the Kishino-Hasegawa (KH) test and the Shimodaira-Hasegawa (SH) test [ 55].
The P-values from this test are calculated using the multi-scale bootstrap technique and are less biased than those of conventional methods [ 57] such as the BS probability (BSP) [ 59], the Kishino-Hasegawa (KH) test [ 60] and the Shimodaira-Hasegawa (SH) test [ 61].
A multi-scale supervised neural architecture, called Multi-Scale SOON, is proposed for natural texture classification.
Firstly, NSCT is employed to decompose the image into multi-scales.
Simulation results show that the Wald CI on logit scale, the Bootstrap percentile CI and the Bias-corrected Bootstrap normal CI have outstanding performance even in small sample designs.
