mdcheck
Purpose
Missing Data Checker and infiller.
Synopsis
[flag,missmap,infilled] = mdcheck(data,options)
options = mdcheck('options')
Description
This function checks for missing data and infills it using a
PCA model if desired. The input is the data to be checked data. Optional input options is described below.
Outputs are the fraction of missing data flag, a map of the locations
of the missing data as an unint8 variable missmap, and the data with the missing values filled
in infilled.
Options
options = a structure array with the following fields:
name: 'options', name indicating that this is an options structure,
options.frac_ssq: [{0.95}]
desired fraction between 0 and 1 of variance to be captured by the PCA model,
options.max_pcs: [{5}]
maximum number of PCs in the model, if 0, then it uses the mean,
options.meancenter: ['no'
| {'yes'}], tells whether to use mean centering in the algorithm,
options.recalcmean: ['no'
| {'yes'}], recalculate mean center after each cycle of replacement (may
improve results for small matricies,
options.display: [{'off'}
| 'on'], governs level of display,
options.tolerance: [{1e-6
100}] convergence criteria, the first element is the minimum change and the
second is the maximum number of iterations,
options.max_missing: [{0.4}]
maximum fraction of missing data with which MDCHECK will operate, and
options.algorithm: [
{'svd'} | 'nipals' ] specified the missing data algorithm to use, NIPALS
typically used for large amounts of missing data or large multi-way arrays.
Note: MDCHECK captures up to options.frac_ssq of the variance using options.max_pcs or fewer
PCA components.
The default options can be retreived using: options = mdcheck('options');.
See Also
parafac, pca
