Description Usage Arguments Value
This function requires having a jade_path
object for the original data
and for data with missing folds. See cv_fit0
.
1 2 | cv_err_binom(orig.path, reads, cv.path.list = NULL,
use.converged.only = TRUE, control.l1 = TRUE, margin = 0.01)
|
orig.path |
Either a path object or a file containing a |
reads |
A matrix of reads corresponding to the data. |
cv.path.list |
Either a list of |
use.converged.only |
Only use fits which have converged. |
control.l1 |
Only use fits with |
A list with elements #'
l1.total
A vector of length N where N is the number of fits in orig.path
giving the total
L1 distance between all pairs of profiles. Equivalent to orig.path$l1.total
.
cv.err.l1
An n.folds
by N matrix where N is the number of fits in orig.path
.
Each row gives the average corss validation error for each value of l1.total
.
err.l1
A vector of length N giving average cross validation error over all folds.
Equivalent to colSums(cv.err.l1)
with missing values for fits that were discarded according to
specification of use.converged.only
and control.l1
.
err.se.l1
Estimated standard error of err.l1
.
cv.min.l1,cv.1se.l1
Indices of the fits in orig.path
corresponding to the minimum and 1
standard error rule cross validation error.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.