2004
DOI: 10.1007/s10822-004-4077-z
|View full text |Cite
|
Sign up to set email alerts
|

Statistical variation in progressive scrambling

Abstract: The two methods most often used to evaluate the robustness and predictivity of partial least squares (PLS) models are cross-validation and response randomization. Both methods may be overly optimistic for data sets that contain redundant observations, however. The kinds of perturbation analysis widely used for evaluating model stability in the context of ordinary least squares regression are only applicable when the descriptors are independent of each other and errors are independent and normally distributed; … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
122
0
1

Year Published

2007
2007
2015
2015

Publication Types

Select...
7
2

Relationship

1
8

Authors

Journals

citations
Cited by 128 publications
(123 citation statements)
references
References 16 publications
0
122
0
1
Order By: Relevance
“…To evaluate the sensitivity of the optimized CoMFA-RF and CoMSIA models to chance correlations, the leave-one-out (LOO), leave 10-out cross-validation and progressive scrambling analyses were performed. 37 The q 2 values of leave 10-out for CoMFA-RF and CoMSIA models without using docking conformer were 0.554 and 0.624 and with using docking conformer were 0.737 and 0.659 respectively. In the progressive scrambling approach, small random perturbations are introduced into a data set and the statistical results.…”
Section: Resultsmentioning
confidence: 92%
“…To evaluate the sensitivity of the optimized CoMFA-RF and CoMSIA models to chance correlations, the leave-one-out (LOO), leave 10-out cross-validation and progressive scrambling analyses were performed. 37 The q 2 values of leave 10-out for CoMFA-RF and CoMSIA models without using docking conformer were 0.554 and 0.624 and with using docking conformer were 0.737 and 0.659 respectively. In the progressive scrambling approach, small random perturbations are introduced into a data set and the statistical results.…”
Section: Resultsmentioning
confidence: 92%
“…The complete details of the progressive scrambling can be find in the reference. 16 In this approach, small random perturbations are introduced into a data set and the statistical results, the perturbation prediction /dr 2 yy' ), are summarized in Table 3. Specifically, in case of five components, the sensitivity to the perturbation d q 2' /dr 2 yy' = 0.994 and the prediction q 2 = 0.487 produced by a progressive scrambling analyses were not dependent on chance correlation.…”
Section: Resultsmentioning
confidence: 99%
“…uated with progressive scrambling analyses. 28 Thirty scrambling were carried with the conditions (maximum = 8 bins, minimum = 2 bins and critical point = 0.85). The susceptibility of the model to chance correlation can be gauged by the slope (dq 2' / dr 2 yy') of q 2 with respect to correlation of the original biological activity versus the scrambled biological activity.…”
Section: Methodsmentioning
confidence: 99%